NeurIPS 2020 Papers

Browse

mini compact topic detail

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Reinforced Molecular Optimization with Neighborhood-Controlled Grammars

Locally Differentially Private (Contextual) Bandits Learning

Online Structured Meta-learning

Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

All Word Embeddings from One Embedding

Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?

Few-Cost Salient Object Detection with Adversarial-Paced Learning

Counterfactual Predictions under Runtime Confounding

BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits

Multipole Graph Neural Operator for Parametric Partial Differential Equations

Fast Unbalanced Optimal Transport on a Tree

Baxter Permutation Process

Generalized Boosting

Probabilistic Active Meta-Learning

Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula

Learning Retrospective Knowledge with Reverse Reinforcement Learning

A Decentralized Parallel Algorithm for Training Generative Adversarial Nets

Bayesian Optimization of Risk Measures

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

Batched Coarse Ranking in Multi-Armed Bandits

Wavelet Flow: Fast Training of High Resolution Normalizing Flows

Minimax Value Interval for Off-Policy Evaluation and Policy Optimization

ShapeFlow: Learnable Deformation Flows Among 3D Shapes

High-Dimensional Sparse Linear Bandits

Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition

Certified Monotonic Neural Networks

Combining Deep Reinforcement Learning and Search for Imperfect-Information Games

Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

Denoised Smoothing: A Provable Defense for Pretrained Classifiers

BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images

Faster DBSCAN via subsampled similarity queries

First-Order Methods for Large-Scale Market Equilibrium Computation

Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings

Multiscale Deep Equilibrium Models

Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings

Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment

On the Similarity between the Laplace and Neural Tangent Kernels

Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs

Matérn Gaussian Processes on Riemannian Manifolds

Adversarially Robust Streaming Algorithms via Differential Privacy

A kernel test for quasi-independence

Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function

Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning

Bayesian Pseudocoresets

MPNet: Masked and Permuted Pre-training for Language Understanding

Improving robustness against common corruptions by covariate shift adaptation

Hard Shape-Constrained Kernel Machines

Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

A Closer Look at the Training Strategy for Modern Meta-Learning

Set2Graph: Learning Graphs From Sets

Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN

Adapting Neural Architectures Between Domains

A mean-field analysis of two-player zero-sum games

Self-Supervised Graph Transformer on Large-Scale Molecular Data

Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning

Learning to search efficiently for causally near-optimal treatments

Supervised Contrastive Learning

Introducing Routing Uncertainty in Capsule Networks

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems

Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates

Deep Energy-based Modeling of Discrete-Time Physics

Learning outside the Black-Box: The pursuit of interpretable models

Faster Wasserstein Distance Estimation with the Sinkhorn Divergence

Scalable Graph Neural Networks via Bidirectional Propagation

Gradient Regularized V-Learning for Dynamic Treatment Regimes

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training

KFC: A Scalable Approximation Algorithm for $k$−center Fair Clustering

Deep Multimodal Fusion by Channel Exchanging

Minimax Classification with 0-1 Loss and Performance Guarantees

Self-Distillation Amplifies Regularization in Hilbert Space

Fighting Copycat Agents in Behavioral Cloning from Observation Histories

GreedyFool: Distortion-Aware Sparse Adversarial Attack

An Efficient Adversarial Attack for Tree Ensembles

Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning

Domain Adaptation as a Problem of Inference on Graphical Models

Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction

Online Matrix Completion with Side Information

Cascaded Text Generation with Markov Transformers

Rankmax: An Adaptive Projection Alternative to the Softmax Function

Stochastic Deep Gaussian Processes over Graphs

Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks

Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks

Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks

Parametric Instance Classification for Unsupervised Visual Feature learning

Robustness of Bayesian Neural Networks to Gradient-Based Attacks

Regularized linear autoencoders recover the principal components, eventually

A Closer Look at Accuracy vs. Robustness

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View

Neural Manifold Ordinary Differential Equations

Robust, Accurate Stochastic Optimization for Variational Inference

On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression

HiPPO: Recurrent Memory with Optimal Polynomial Projections

Ultrahyperbolic Representation Learning

Fair Multiple Decision Making Through Soft Interventions

Finding the Homology of Decision Boundaries with Active Learning

Neural Sparse Representation for Image Restoration

Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting

Unsupervised Representation Learning by Invariance Propagation

How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization

Learning to Adapt to Evolving Domains

Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

SIRI: Spatial Relation Induced Network For Spatial Description Resolution

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets

Attribute Prototype Network for Zero-Shot Learning

Decisions, Counterfactual Explanations and Strategic Behavior

Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis

Learning to Prove Theorems by Learning to Generate Theorems

MeshSDF: Differentiable Iso-Surface Extraction

Error Bounds of Imitating Policies and Environments

Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning

BERT Loses Patience: Fast and Robust Inference with Early Exit

How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions

Rethinking Learnable Tree Filter for Generic Feature Transform

SOLOv2: Dynamic and Fast Instance Segmentation

Latent Template Induction with Gumbel-CRFs

Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection

A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent

Neural Methods for Point-wise Dependency Estimation

Bayesian Deep Ensembles via the Neural Tangent Kernel

Robust Optimization for Fairness with Noisy Protected Groups

Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation

Towards Playing Full MOBA Games with Deep Reinforcement Learning

Robust compressed sensing using generative models

On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems

Statistical control for spatio-temporal MEG/EEG source imaging with desparsified mutli-task Lasso

Flows for simultaneous manifold learning and density estimation

Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising

A graph similarity for deep learning

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features

Minimax Bounds for Generalized Linear Models

Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals

Probabilistic Linear Solvers for Machine Learning

Feature Importance Ranking for Deep Learning

MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures

HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Loss

Modeling Shared responses in Neuroimaging Studies through MultiView ICA

Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency

Semialgebraic Optimization for Lipschitz Constants of ReLU Networks

System Identification with Biophysical Constraints: A Circuit Model of the Inner Retina

Auditing Differentially Private Machine Learning: How Private is Private SGD?

Robust Meta-learning for Mixed Linear Regression with Small Batches

Deep active inference agents using Monte-Carlo methods

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping

Coresets via Bilevel Optimization for Continual Learning and Streaming

Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling

Self-Adaptive Training: beyond Empirical Risk Minimization

On the distance between two neural networks and the stability of learning

GPS-Net: Graph-based Photometric Stereo Network

Adversarial Self-Supervised Contrastive Learning

Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization

Passport-aware Normalization for Deep Model Protection

Neural Architecture Generator Optimization

The Power of Predictions in Online Control

Multi-label Contrastive Predictive Coding

One-sample Guided Object Representation Disassembling

Learning Dynamic Belief Graphs to Generalize on Text-Based Games

Hybrid Models for Learning to Branch

Provable Overlapping Community Detection in Weighted Graphs

Calibrating CNNs for Lifelong Learning

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Adaptive Reduced Rank Regression

Permute-and-Flip: A new mechanism for differentially private selection

Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control

Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings

SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks

Avoiding Side Effects in Complex Environments

Adversarial Weight Perturbation Helps Robust Generalization

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

A new convergent variant of Q-learning with linear function approximation

A Boolean Task Algebra for Reinforcement Learning

Continuous Regularized Wasserstein Barycenters

Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms

Coherent Hierarchical Multi-Label Classification Networks

Learning Disentangled Representations and Group Structure of Dynamical Environments

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

Stochastic Normalization

In search of robust measures of generalization

RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces

Incorporating BERT into Parallel Sequence Decoding with Adapters

Sharper Generalization Bounds for Pairwise Learning

Hierarchical Quantized Autoencoders

Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping

Provably Consistent Partial-Label Learning

Transferable Calibration with Lower Bias and Variance in Domain Adaptation

ICNet: Intra-saliency Correlation Network for Co-Saliency Detection

Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits

A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices

SGD with shuffling: optimal rates without component convexity and large epoch requirements

A Dictionary Approach to Domain-Invariant Learning in Deep Networks

A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

Adversarial Bandits with Corruptions

Active Invariant Causal Prediction: Experiment Selection through Stability

Adaptive Online Estimation of Piecewise Polynomial Trends

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Neural Unsigned Distance Fields for Implicit Function Learning

Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition

Near-Optimal Comparison Based Clustering

Robust large-margin learning in hyperbolic space

LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration

No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix

Cross-Scale Internal Graph Neural Network for Image Super-Resolution

Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

Blind Video Temporal Consistency via Deep Video Prior

A mathematical model for automatic differentiation in machine learning

Auxiliary Task Reweighting for Minimum-data Learning

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification

Theory-Inspired Path-Regularized Differential Network Architecture Search

Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition

Agnostic $Q$-learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample Complexity

Compositional Generalization by Learning Analytical Expressions

Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards

Approximation Based Variance Reduction for Reparameterization Gradients

Swapping Autoencoder for Deep Image Manipulation

ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding

Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning

A Group-Theoretic Framework for Data Augmentation

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

Learning Individually Inferred Communication for Multi-Agent Cooperation

Exponential ergodicity of mirror-Langevin diffusions

Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting

Deep Reinforcement and InfoMax Learning

DISK: Learning local features with policy gradient

Content Provider Dynamics and Coordination in Recommendation Ecosystems

Projection Robust Wasserstein Distance and Riemannian Optimization

Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms

Proximity Operator of the Matrix Perspective Function and its Applications

Robust Quantization: One Model to Rule Them All

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

Backpropagating Linearly Improves Transferability of Adversarial Examples

Dual-Free Stochastic Decentralized Optimization with Variance Reduction

CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching

Compositional Zero-Shot Learning via Fine-Grained Dense Feature Composition

Gradient Surgery for Multi-Task Learning

On the Trade-off between Adversarial and Backdoor Robustness

Graph Cross Networks with Vertex Infomax Pooling

MetaSDF: Meta-Learning Signed Distance Functions

Adaptive Gradient Quantization for Data-Parallel SGD

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators

Deep reconstruction of strange attractors from time series

SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free

Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?

Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping

Stable and expressive recurrent vision models

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

Texture Interpolation for Probing Visual Perception

Off-Policy Imitation Learning from Observations

AdaTune: Adaptive Tensor Program Compilation Made Efficient

Neural Non-Rigid Tracking

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

The Diversified Ensemble Neural Network

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis

Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks

The Generalized Lasso with Nonlinear Observations and Generative Priors

Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs

Learning Loss for Test-Time Augmentation

Learning to Learn Variational Semantic Memory

Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method

The Pitfalls of Simplicity Bias in Neural Networks

LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-resolution and Beyond

Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks

Sparse Learning with CART

Learning About Objects by Learning to Interact with Them

Fast and Flexible Temporal Point Processes with Triangular Maps

UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection

Deep Diffusion-Invariant Wasserstein Distributional Classification

Kernel Based Progressive Distillation for Adder Neural Networks

Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes

Beta R-CNN: Looking into Pedestrian Detection from Another Perspective

HOI Analysis: Integrating and Decomposing Human-Object Interaction

Softmax Deep Double Deterministic Policy Gradients

RANet: Region Attention Network for Semantic Segmentation

Practical Quasi-Newton Methods for Training Deep Neural Networks

Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation

PIE-NET: Parametric Inference of Point Cloud Edges

A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

Continual Learning with Node-Importance based Adaptive Group Sparse Regularization

SCOP: Scientific Control for Reliable Neural Network Pruning

Learning to Orient Surfaces by Self-supervised Spherical CNNs

Assessing SATNet's Ability to Solve the Symbol Grounding Problem

Unfolding the Alternating Optimization for Blind Super Resolution

StratLearner: Learning a Strategy for Misinformation Prevention in Social Networks

Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation

Group Contextual Encoding for 3D Point Clouds

Pruning Filter in Filter

Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts

Adversarially Robust Few-Shot Learning: A Meta-Learning Approach

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses

Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning

Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

Learning from Positive and Unlabeled Data with Arbitrary Positive Shift

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

Sample Complexity of Uniform Convergence for Multicalibration

Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations

A Class of Algorithms for General Instrumental Variable Models

EcoLight: Intersection Control in Developing Regions Under Extreme Budget and Network Constraints

Transfer Learning via $\ell_1$ Regularization

What if Neural Networks had SVDs?

Searching for Low-Bit Weights in Quantized Neural Networks

Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback

Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation

AvE: Assistance via Empowerment

Minibatch vs Local SGD for Heterogeneous Distributed Learning

Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems

DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

Accelerating Reinforcement Learning through GPU Atari Emulation

Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

Practical Low-Rank Communication Compression in Decentralized Deep Learning

Wisdom of the Ensemble: Improving Consistency of Deep Learning Models

Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization

A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

An Unbiased Risk Estimator for Learning with Augmented Classes

Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

A Tight Lower Bound and Efficient Reduction for Swap Regret

Improved Schemes for Episodic Memory-based Lifelong Learning

Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher

The Adaptive Complexity of Maximizing a Gross Substitutes Valuation

UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging

PLANS: Neuro-Symbolic Program Learning from Videos

Decision-Making with Auto-Encoding Variational Bayes

Weakly Supervised Deep Functional Maps for Shape Matching

Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards

Bayesian Probabilistic Numerical Integration with Tree-Based Models

Fairness constraints can help exact inference in structured prediction

Multiparameter Persistence Image for Topological Machine Learning

Heuristic Domain Adaptation

Probabilistic Time Series Forecasting with Shape and Temporal Diversity

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Labelling unlabelled videos from scratch with multi-modal self-supervision

On the Convergence of Smooth Regularized Approximate Value Iteration Schemes

Reliable Graph Neural Networks via Robust Aggregation

Random Walk Graph Neural Networks

AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection

ConvBERT: Improving BERT with Span-based Dynamic Convolution

On the training dynamics of deep networks with $L_2$ regularization

Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings

Prophet Attention: Predicting Attention with Future Attention

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples

3D Self-Supervised Methods for Medical Imaging

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows

SMYRF - Efficient Attention using Asymmetric Clustering

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot

Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks

Self-supervised Co-Training for Video Representation Learning

Further Analysis of Outlier Detection with Deep Generative Models

Hamiltonian Monte Carlo using an adjoint-differentiated Laplace approximation: Bayesian inference for latent Gaussian models and beyond

Bandit Linear Control

Is normalization indispensable for training deep neural network?

Unsupervised Sound Separation Using Mixture Invariant Training

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data

Space-Time Correspondence as a Contrastive Random Walk

On Warm-Starting Neural Network Training

Generative View Synthesis: From Single-view Semantics to Novel-view Images

Critic Regularized Regression

Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding

Learnability with Indirect Supervision Signals

Adaptive Probing Policies for Shortest Path Routing

CoinPress: Practical Private Mean and Covariance Estimation

Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth

Private Identity Testing for High-Dimensional Distributions

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

Meta-Gradient Reinforcement Learning with an Objective Discovered Online

Neural Networks with Small Weights and Depth-Separation Barriers

Riemannian Continuous Normalizing Flows

Path Integral Based Convolution and Pooling for Graph Neural Networks

Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction

Certifying Confidence via Randomized Smoothing

A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network

A General Method for Robust Learning from Batches

Few-shot Image Generation with Elastic Weight Consolidation

Dual Instrumental Variable Regression

Learning Kernel Tests Without Data Splitting

Towards More Practical Adversarial Attacks on Graph Neural Networks

Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning

f-Divergence Variational Inference

Implicit Graph Neural Networks

Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification

Quantitative Propagation of Chaos for SGD in Wide Neural Networks

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

Learning Some Popular Gaussian Graphical Models without Condition Number Bounds

Neural Networks Fail to Learn Periodic Functions and How to Fix It

Strongly Incremental Constituency Parsing with Graph Neural Networks

Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows

Improving model calibration with accuracy versus uncertainty optimization

Continuous Surface Embeddings

A General Large Neighborhood Search Framework for Solving Integer Linear Programs

High-contrast “gaudy” images improve the training of deep neural network models of visual cortex

Simple and Fast Algorithm for Binary Integer and Online Linear Programming

OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling

CO-Optimal Transport

Explicit Regularisation in Gaussian Noise Injections

Assisted Learning: A Framework for Multi-Organization Learning

Deep Smoothing of the Implied Volatility Surface

Limits to Depth Efficiencies of Self-Attention

A Unifying View of Optimism in Episodic Reinforcement Learning

Adversarial Distributional Training for Robust Deep Learning

GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification

BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization

Multilabel Classification by Hierarchical Partitioning and Data-dependent Grouping

A Study on Encodings for Neural Architecture Search

Task-Robust Model-Agnostic Meta-Learning

On the equivalence of molecular graph convolution and molecular wave function with poor basis set

One-bit Supervision for Image Classification

CompRess: Self-Supervised Learning by Compressing Representations

Learning Global Transparent Models consistent with Local Contrastive Explanations

Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate

Learning discrete distributions: user vs item-level privacy

Self-Learning Transformations for Improving Gaze and Head Redirection

Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts

Robust Density Estimation under Besov IPM Losses

Stochasticity of Deterministic Gradient Descent: Large Learning Rate for Multiscale Objective Function

Object Goal Navigation using Goal-Oriented Semantic Exploration

Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks

PAC-Bayes Analysis Beyond the Usual Bounds

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

Video Frame Interpolation without Temporal Priors

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach

Bad Global Minima Exist and SGD Can Reach Them

Efficient Exact Verification of Binarized Neural Networks

Myersonian Regression

Learning under Model Misspecification: Applications to Variational and Ensemble methods

Generating Correct Answers for Progressive Matrices Intelligence Tests

Universally Quantized Neural Compression

The Strong Screening Rule for SLOPE

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings

Evolving Normalization-Activation Layers

Curriculum By Smoothing

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

Directional Pruning of Deep Neural Networks

Task-Oriented Feature Distillation

Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry

Minibatch Stochastic Approximate Proximal Point Methods

LoCo: Local Contrastive Representation Learning

Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems

Multi-task Batch Reinforcement Learning with Metric Learning

Evaluating Attribution for Graph Neural Networks

Learning Strategic Network Emergence Games

Detecting Hands and Recognizing Physical Contact in the Wild

Focus of Attention Improves Information Transfer in Visual Features

Adversarial Attacks on Linear Contextual Bandits

Neural Path Features and Neural Path Kernel : Understanding the role of gates in deep learning

Deep Transformation-Invariant Clustering

HYDRA: Pruning Adversarially Robust Neural Networks

Higher-Order Certification For Randomized Smoothing

Exactly Computing the Local Lipschitz Constant of ReLU Networks

A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

Learning to Learn with Feedback and Local Plasticity

Model Interpretability through the Lens of Computational Complexity

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

A Unified View of Label Shift Estimation

Distributional Robustness with IPMs and links to Regularization and GANs

On the universality of deep learning

CogLTX: Applying BERT to Long Texts

What shapes feature representations? Exploring datasets, architectures, and training

Better Full-Matrix Regret via Parameter-Free Online Learning

Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement

On Correctness of Automatic Differentiation for Non-Differentiable Functions

Consistent Estimation of Identifiable Nonparametric Mixture Models from Grouped Observations

GAN Memory with No Forgetting

Approximate Heavily-Constrained Learning with Lagrange Multiplier Models

Denoising Diffusion Probabilistic Models

Variational Bayesian Monte Carlo with Noisy Likelihoods

SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence

Exchangeable Neural ODE for Set Modeling

Bootstrapping neural processes

Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization

Is Long Horizon RL More Difficult Than Short Horizon RL?

Graph Information Bottleneck

Inverse Reinforcement Learning from a Gradient-based Learner

Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses

Statistical and Topological Properties of Sliced Probability Divergences

Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method

Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization

SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection

WOR and $p$'s: Sketches for $\ell_p$-Sampling Without Replacement

Robust Persistence Diagrams using Reproducing Kernels

Biologically Inspired Mechanisms for Adversarial Robustness

Variance reduction for Random Coordinate Descent-Langevin Monte Carlo

Predictive inference is free with the jackknife+-after-bootstrap

Online learning with dynamics: A minimax perspective

Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks

Improving Online Rent-or-Buy Algorithms with Sequential Decision Making and ML Predictions

Submodular Maximization Through Barrier Functions

Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks

How many samples is a good initial point worth in Low-rank Matrix Recovery?

Finite Versus Infinite Neural Networks: an Empirical Study

Online Planning with Lookahead Policies

Non-Convex SGD Learns Halfspaces with Adversarial Label Noise

Improving Sparse Vector Technique with Renyi Differential Privacy

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

Watch out! Motion is Blurring the Vision of Your Deep Neural Networks

Diverse Image Captioning with Context-Object Split Latent Spaces

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

The Discrete Gaussian for Differential Privacy

Relative gradient optimization of the Jacobian term in unsupervised deep learning

Implicit Neural Representations with Periodic Activation Functions

Autoregressive Score Matching

Preference learning along multiple criteria: A game-theoretic perspective

TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation

Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks

Towards Learning Convolutions from Scratch

Learning Differential Equations that are Easy to Solve

Online Algorithm for Unsupervised Sequential Selection with Contextual Information

A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration

Compositional Generalization via Neural-Symbolic Stack Machines

Post-training Iterative Hierarchical Data Augmentation for Deep Networks

AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference

BOSS: Bayesian Optimization over String Spaces

Adversarial Training is a Form of Data-dependent Operator Norm Regularization

Trust the Model When It Is Confident: Masked Model-based Actor-Critic

Avoiding Side Effects By Considering Future Tasks

Implicit Rank-Minimizing Autoencoder

RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

Decentralized Langevin Dynamics for Bayesian Learning

Monotone operator equilibrium networks

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

Neurosymbolic Transformers for Multi-Agent Communication

Federated Principal Component Analysis

When Do Neural Networks Outperform Kernel Methods?

Universal Domain Adaptation through Self Supervision

Uncertainty-aware Self-training for Few-shot Text Classification

Differentially-Private Federated Linear Bandits

What went wrong and when? Instance-wise feature importance for time-series black-box models

Achieving Equalized Odds by Resampling Sensitive Attributes

Model Agnostic Multilevel Explanations

Online MAP Inference of Determinantal Point Processes

High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds

Multi-agent active perception with prediction rewards

Synbols: Probing Learning Algorithms with Synthetic Datasets

Learning Augmented Energy Minimization via Speed Scaling

Efficient Projection-free Algorithms for Saddle Point Problems

Improved Guarantees for k-means++ and k-means++ Parallel

Dissecting Neural ODEs

Higher-Order Spectral Clustering of Directed Graphs

Ensembling geophysical models with Bayesian Neural Networks

Optimal Private Median Estimation under Minimal Distributional Assumptions

Rethinking Importance Weighting for Deep Learning under Distribution Shift

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

Recovery of sparse linear classifiers from mixture of responses

Neural Execution Engines: Learning to Execute Subroutines

The Autoencoding Variational Autoencoder

Generative 3D Part Assembly via Dynamic Graph Learning

Unsupervised Text Generation by Learning from Search

Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe

Logarithmic Pruning is All You Need

Online Adaptation for Consistent Mesh Reconstruction in the Wild

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

Meta-Neighborhoods

Fair Performance Metric Elicitation

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

Curriculum learning for multilevel budgeted combinatorial problems

Ratio Trace Formulation of Wasserstein Discriminant Analysis

Self-Supervised Relationship Probing

Hard Negative Mixing for Contrastive Learning

Self-Supervised Generative Adversarial Compression

Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks

Domain Generalization via Entropy Regularization

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

Equivariant Networks for Hierarchical Structures

Model Fusion via Optimal Transport

H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks

Robustness of Community Detection to Random Geometric Perturbations

Co-Tuning for Transfer Learning

A new inference approach for training shallow and deep generalized linear models of noisy interacting neurons

Optimal Adaptive Electrode Selection to Maximize Simultaneously Recorded Neuron Yield

Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model

Towards Problem-dependent Optimal Learning Rates

Towards Convergence Rate Analysis of Random Forests for Classification

Neural Controlled Differential Equations for Irregular Time Series

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning

High-recall causal discovery for autocorrelated time series with latent confounders

The Smoothed Possibility of Social Choice

R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making

Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning

Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence

Parameterized Explainer for Graph Neural Network

Finding All $\epsilon$-Good Arms in Stochastic Bandits

Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients

Deep Archimedean Copulas

Deep Transformers with Latent Depth

Learning the Linear Quadratic Regulator from Nonlinear Observations

Factor Graph Neural Networks

Teaching a GAN What Not to Learn

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Learning Causal Effects via Weighted Empirical Risk Minimization

Audeo: Audio Generation for a Silent Performance Video

Stochastic Normalizing Flows

Learning Bounds for Risk-sensitive Learning

Instance-wise Feature Grouping

On the Power of Louvain in the Stochastic Block Model

Variational Bayesian Unlearning

Consequences of Misaligned AI

Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

Fast Adaptive Non-Monotone Submodular Maximization Subject to a Knapsack Constraint

A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding

RD$^2$: Reward Decomposition with Representation Decomposition

Modeling Noisy Annotations for Crowd Counting

Robust Correction of Sampling Bias using Cumulative Distribution Functions

Graph Geometry Interaction Learning

Lipschitz Bounds and Provably Robust Training by Laplacian Smoothing

Improving Local Identifiability in Probabilistic Box Embeddings

Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates

Model Class Reliance for Random Forests

Distribution-free binary classification: prediction sets, confidence intervals and calibration

Agnostic Learning with Multiple Objectives

Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention

Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning

Pre-training via Paraphrasing

Improving Inference for Neural Image Compression

Learning abstract structure for drawing by efficient motor program induction

Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing

Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss

Certified Defense to Image Transformations via Randomized Smoothing

Partial Optimal Transport with applications on Positive-Unlabeled Learning

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?

Interpretable Sequence Learning for Covid-19 Forecasting

On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces

High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization

On Power Laws in Deep Ensembles

Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds

The Potts-Ising model for discrete multivariate data

Gibbs Sampling with People

PRANK: motion Prediction based on RANKing

Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences

On the Error Resistance of Hinge-Loss Minimization

Efficient Planning in Large MDPs with Weak Linear Function Approximation

Coresets for Near-Convex Functions

The Primal-Dual method for Learning Augmented Algorithms

Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration

Network Diffusions via Neural Mean-Field Dynamics

Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class

Incorporating Interpretable Output Constraints in Bayesian Neural Networks

Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Estimating Rank-One Spikes from Heavy-Tailed Noise via Self-Avoiding Walks

Belief Propagation Neural Networks

Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point

Gradient Boosted Normalizing Flows

Testing Determinantal Point Processes

Rethinking pooling in graph neural networks

Efficient estimation of neural tuning during naturalistic behavior

Sparse Weight Activation Training

Adapting to Misspecification in Contextual Bandits

Conformal Symplectic and Relativistic Optimization

Transferable Graph Optimizers for ML Compilers

Throughput-Optimal Topology Design for Cross-Silo Federated Learning

General Transportability of Soft Interventions: Completeness Results

CoSE: Compositional Stroke Embeddings

Factor Graph Grammars

Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples

Online Neural Connectivity Estimation with Noisy Group Testing

Autoencoders that don't overfit towards the Identity

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

Understanding Global Feature Contributions With Additive Importance Measures

Non-reversible Gaussian processes for identifying latent dynamical structure in neural data

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Adversarial Attacks on Deep Graph Matching

Contrastive learning of global and local features for medical image segmentation with limited annotations

Provably adaptive reinforcement learning in metric spaces

Towards Safe Policy Improvement for Non-Stationary MDPs

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

Generative Neurosymbolic Machines

Non-Euclidean Universal Approximation

Off-Policy Interval Estimation with Lipschitz Value Iteration

Optimal Prediction of the Number of Unseen Species with Multiplicity

A Single Recipe for Online Submodular Maximization with Adversarial or Stochastic Constraints

Adaptation Properties Allow Identification of Optimized Neural Codes

Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs

Skeleton-bridged Point Completion: From Global Inference to Local Adjustment

CryptoNAS: Private Inference on a ReLU Budget

Experimental design for MRI by greedy policy search

CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models

Training Generative Adversarial Networks by Solving Ordinary Differential Equations

Policy Improvement via Imitation of Multiple Oracles

Outlier Robust Mean Estimation with Subgaussian Rates via Stability

An Analysis of SVD for Deep Rotation Estimation

Learning Physical Constraints with Neural Projections

Characterizing emergent representations in a space of candidate learning rules for deep networks

Information Theoretic Regret Bounds for Online Nonlinear Control

Learning sparse codes from compressed representations with biologically plausible local wiring constraints

Reparameterizing Mirror Descent as Gradient Descent

Few-shot Visual Reasoning with Meta-Analogical Contrastive Learning

Learning efficient task-dependent representations with synaptic plasticity

Primal-Dual Mesh Convolutional Neural Networks

Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms

Stein Self-Repulsive Dynamics: Benefits From Past Samples

Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions

Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes

Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search

Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition

DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

All-or-nothing statistical and computational phase transitions in sparse spiked matrix estimation

Fourier Spectrum Discrepancies in Deep Network Generated Images

Adaptive Shrinkage Estimation for Streaming Graphs

Provably Good Batch Reinforcement Learning Without Great Exploration

A/B Testing in Dense Large-Scale Networks: Design and Inference

Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes

Replica-Exchange Nos\'e-Hoover Dynamics for Bayesian Learning on Large Datasets

Learning compositional functions via multiplicative weight updates

Optimal Best-arm Identification in Linear Bandits

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

A Unified Switching System Perspective and Convergence Analysis of Q-Learning Algorithms

Adaptive Discretization for Model-Based Reinforcement Learning

De-Anonymizing Text by Fingerprinting Language Generation

Low Distortion Block-Resampling with Spatially Stochastic Networks

Greedy inference with structure-exploiting lazy maps

Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC

Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

Semantic Visual Navigation by Watching YouTube Videos

End-to-End Learning and Intervention in Games

Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases

Compositional Explanations of Neurons

Big Self-Supervised Models are Strong Semi-Supervised Learners

Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests

Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation

Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses

The Wasserstein Proximal Gradient Algorithm

Axioms for Learning from Pairwise Comparisons

Generative causal explanations of black-box classifiers

What is being transferred in transfer learning?

Recurrent Quantum Neural Networks

Latent Bandits Revisited

Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning

Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning

A convex optimization formulation for multivariate regression

Confidence sequences for sampling without replacement

Adaptive Learning of Rank-One Models for Efficient Pairwise Sequence Alignment

User-Dependent Neural Sequence Models for Continuous-Time Event Data

Big Bird: Transformers for Longer Sequences

PLLay: Efficient Topological Layer based on Persistent Landscapes

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems

Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments

JAX MD: A Framework for Differentiable Physics

Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity

NeuMiss networks: differentiable programming for supervised learning with missing values.

Task-Agnostic Amortized Inference of Gaussian Process Hyperparameters

Self-supervised learning through the eyes of a child

Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks

Point process models for sequence detection in high-dimensional neural spike trains

Learning to Approximate a Bregman Divergence

Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples

Probably Approximately Correct Constrained Learning

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology

Deep Subspace Clustering with Data Augmentation

Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses

Meta-Learning with Adaptive Hyperparameters

Estimating weighted areas under the ROC curve

Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models

Certifiably Adversarially Robust Detection of Out-of-Distribution Data

Interpolation Technique to Speed Up Gradients Propagation in Neural ODEs

TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning

Projected Stein Variational Gradient Descent

Learning to summarize with human feedback

PEP: Parameter Ensembling by Perturbation

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks

Understanding spiking networks through convex optimization

A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling

Neural FFTs for Universal Texture Image Synthesis

Limits on Testing Structural Changes in Ising Models

A Simple Language Model for Task-Oriented Dialogue

Bayesian Bits: Unifying Quantization and Pruning

Acceleration with a Ball Optimization Oracle

Almost Surely Stable Deep Dynamics

A causal view of compositional zero-shot recognition

Sample complexity and effective dimension for regression on manifolds

An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits

Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations

Instance Selection for GANs

Temporal Variability in Implicit Online Learning

Fast geometric learning with symbolic matrices

Neural Topographic Factor Analysis for fMRI Data

Inferring learning rules from animal decision-making

Simultaneous Preference and Metric Learning from Paired Comparisons

Towards practical differentially private causal graph discovery

Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision

Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

The Mean-Squared Error of Double Q-Learning

Convolutional Tensor-Train LSTM for Spatio-Temporal Learning

Improving GAN Training with Probability Ratio Clipping and Sample Reweighting

Top-KAST: Top-K Always Sparse Training

Disentangling Human Error from Ground Truth in Segmentation of Medical Images

Model Selection in Contextual Stochastic Bandit Problems

Modular Meta-Learning with Shrinkage

Calibrating Deep Neural Networks using Focal Loss

Discovering conflicting groups in signed networks

Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians

Distribution Matching for Crowd Counting

ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

Consistent Plug-in Classifiers for Complex Objectives and Constraints

Collapsing Bandits and Their Application to Public Health Intervention

An Optimal Elimination Algorithm for Learning a Best Arm

Adaptive Learned Bloom Filter (Ada-BF): Efficient Utilization of the Classifier with Application to Real-Time Information Filtering on the Web

Information-theoretic Task Selection for Meta-Reinforcement Learning

Learning Multi-Agent Communication through Structured Attentive Reasoning

Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

Steady State Analysis of Episodic Reinforcement Learning

Active Structure Learning of Causal DAGs via Directed Clique Trees

Normalizing Kalman Filters for Multivariate Time Series Analysis

Early-Learning Regularization Prevents Memorization of Noisy Labels

Learning Feature Sparse Principal Subspace

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality

POMDPs in Continuous Time and Discrete Spaces

Goal-directed Generation of Discrete Structures with Conditional Generative Models

Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence

Multi-agent Trajectory Prediction with Fuzzy Query Attention

Linear Dynamical Systems as a Core Computational Primitive

GramGAN: Deep 3D Texture Synthesis From 2D Exemplars

Finer Metagenomic Reconstruction via Biodiversity Optimization

Measuring Systematic Generalization in Neural Proof Generation with Transformers

Directional convergence and alignment in deep learning

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

Efficient semidefinite-programming-based inference for binary and multi-class MRFs

On the linearity of large non-linear models: when and why the tangent kernel is constant

Quantized Variational Inference

Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization

The Value Equivalence Principle for Model-Based Reinforcement Learning

Organizing recurrent network dynamics by task-computation to enable continual learning

The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification

Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking

Escaping the Gravitational Pull of Softmax

Forethought and Hindsight in Credit Assignment

When Counterpoint Meets Chinese Folk Melodies

The Statistical Complexity of Early-Stopped Mirror Descent

A Local Temporal Difference Code for Distributional Reinforcement Learning

Rescuing neural spike train models from bad MLE

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning

The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise

Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets

Hypersolvers: Toward Fast Continuous-Depth Models

Comparator-Adaptive Convex Bandits

Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks

STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks

Variational Amodal Object Completion

Novelty Search in Representational Space for Sample Efficient Exploration

RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning

Deeply Learned Spectral Total Variation Decomposition

Manifold structure in graph embeddings

Exploiting the Surrogate Gap in Online Multiclass Classification

ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool

Secretary and Online Matching Problems with Machine Learned Advice

Estimating Fluctuations in Neural Representations of Uncertain Environments

Sliding Window Algorithms for k-Clustering Problems

Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

Coresets for Robust Training of Deep Neural Networks against Noisy Labels

Unsupervised Learning of Object Landmarks via Self-Training Correspondence

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Black-Box Optimization with Local Generative Surrogates

Entropic Causal Inference: Identifiability and Finite Sample Results

UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging

Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games

Counterfactual Data Augmentation using Locally Factored Dynamics

Convolutional Generation of Textured 3D Meshes

Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks

Joint Policy Search for Multi-agent Collaboration with Imperfect Information

Invertible Gaussian Reparameterization: Revisiting the Gumbel-Softmax

Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm

Linear Time Sinkhorn Divergences using Positive Features

Applications of Common Entropy for Causal Inference

SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm

Network-to-Network Translation with Conditional Invertible Neural Networks

ColdGANs: Taming Language GANs with Cautious Sampling Strategies

Minimax Estimation of Conditional Moment Models

Second Order PAC-Bayesian Bounds for the Weighted Majority Vote

Kernel Methods Through the Roof: Handling Billions of Points Efficiently

Learning of Discrete Graphical Models with Neural Networks

Spin-Weighted Spherical CNNs

SnapBoost: A Heterogeneous Boosting Machine

Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian

Ensemble Distillation for Robust Model Fusion in Federated Learning

PAC-Bayes Learning Bounds for Sample-Dependent Priors

Fair regression via plug-in estimator and recalibration with statistical guarantees

Sampling from a k-DPP without looking at all items

Geometric Dataset Distances via Optimal Transport

Fair regression with Wasserstein barycenters

Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs

A polynomial-time algorithm for learning nonparametric causal graphs

Convex optimization based on global lower second-order models

Incorporating Pragmatic Reasoning Communication into Emergent Language

Deep Evidential Regression

Learning discrete distributions with infinite support

Curvature Regularization to Prevent Distortion in Graph Embedding

What Do Neural Networks Learn When Trained With Random Labels?

A novel variational form of the Schatten-$p$ quasi-norm

Robust Disentanglement of a Few Factors at a Time using rPU-VAE

Improved Analysis of Clipping Algorithms for Non-convex Optimization

Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications

A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization

On Infinite-Width Hypernetworks

Discovering Symbolic Models from Deep Learning with Inductive Biases

Online Meta-Critic Learning for Off-Policy Actor-Critic Methods

Learning to solve TV regularised problems with unrolled algorithms

Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms.

Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumes

Hardness of Learning Neural Networks with Natural Weights

Identifying signal and noise structure in neural population activity with Gaussian process factor models

A Bandit Learning Algorithm and Applications to Auction Design

Joints in Random Forests

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Deep Metric Learning with Spherical Embedding

Triple descent and the two kinds of overfitting: where & why do they appear?

Neuronal Gaussian Process Regression

Continual Deep Learning by Functional Regularisation of Memorable Past

Weak Form Generalized Hamiltonian Learning

DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling

HRN: A Holistic Approach to One Class Learning

Train-by-Reconnect: Decoupling Locations of Weights from Their Values

All your loss are belong to Bayes

Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds

Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs

AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control

Graph Policy Network for Transferable Active Learning on Graphs

Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity

Correspondence learning via linearly-invariant embedding

Optimal visual search based on a model of target detectability in natural images

Deep Rao-Blackwellised Particle Filters for Time Series Forecasting

Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation

Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

Coresets for Regressions with Panel Data

Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration

An efficient nonconvex reformulation of stagewise convex optimization problems

Conservative Q-Learning for Offline Reinforcement Learning

Probabilistic Orientation Estimation with Matrix Fisher Distributions

Learning from Failure: De-biasing Classifier from Biased Classifier

Safe Reinforcement Learning via Curriculum Induction

Telescoping Density-Ratio Estimation

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

Stochastic Optimization with Laggard Data Pipelines

Learning to Detect Objects with a 1 Megapixel Event Camera

Online Learning in Contextual Bandits using Gated Linear Networks

Online Sinkhorn: Optimal Transport distances from sample streams

Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

Self-Adaptively Learning to Demoiré from Focused and Defocused Image Pairs

Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring

Non-parametric Models for Non-negative Functions

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

Trading Personalization for Accuracy: Data Debugging in Collaborative Filtering

Meta-learning from Tasks with Heterogeneous Attribute Spaces

Fast and Accurate $k$-means++ via Rejection Sampling

Regularizing Towards Permutation Invariance In Recurrent Models

Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning

Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret

Bayesian Robust Optimization for Imitation Learning

Auto Learning Attention

Benchmarking Deep Learning Interpretability in Time Series Predictions

Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network

Promoting Stochasticity for Expressive Policies via a Simple and Efficient Regularization Method

Contextual Games: Multi-Agent Learning with Side Information

Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks

Semi-Supervised Neural Architecture Search

Continual Learning in Low-rank Orthogonal Subspaces

Learning to Play Sequential Games versus Unknown Opponents

A Universal Approximation Theorem of Deep Neural Networks for Expressing Probability Distributions

Collegial Ensembles

Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems

Recursive Inference for Variational Autoencoders

MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics

MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles

Curriculum Learning by Dynamic Instance Hardness

Inverting Gradients - How easy is it to break privacy in federated learning?

Efficient Clustering for Stretched Mixtures: Landscape and Optimality

Learning Restricted Boltzmann Machines with Sparse Latent Variables

Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs

Understanding and Improving Fast Adversarial Training

PyGlove: Symbolic Programming for Automated Machine Learning

How do fair decisions fare in long-term qualification?

DynaBERT: Dynamic BERT with Adaptive Width and Depth

On the Expressiveness of Approximate Inference in Bayesian Neural Networks

Reinforcement Learning for Control with Multiple Frequencies

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

A Scalable Approach for Privacy-Preserving Collaborative Machine Learning

CrossTransformers: spatially-aware few-shot transfer

Multimodal Graph Networks for Compositional Generalization in Visual Question Answering

Margins are Insufficient for Explaining Gradient Boosting

Interferobot: aligning an optical interferometer by a reinforcement learning agent

Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes

Robust Reinforcement Learning via Adversarial training with Langevin Dynamics

Object-Centric Learning with Slot Attention

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

An Improved Analysis of Stochastic Gradient Descent with Momentum

Dark Experience for General Continual Learning: a Strong, Simple Baseline

Bidirectional Convolutional Poisson Gamma Dynamical Systems

Language Through a Prism: A Spectral Approach for Multiscale Language Representations

Language Models are Few-Shot Learners

Counterfactual Vision-and-Language Navigation: Unravelling the Unseen

Instance Based Approximations to Profile Maximum Likelihood

CoMIR: Contrastive Multimodal Image Representation for Registration

Latent World Models For Intrinsically Motivated Exploration

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games

Evaluating and Rewarding Teamwork Using Cooperative Game Abstractions

Deep Variational Instance Segmentation

Bandit Samplers for Training Graph Neural Networks

Cycle-Contrast for Self-Supervised Video Representation Learning

Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate

Planning in Markov Decision Processes with Gap-Dependent Sample Complexity

Hierarchical Poset Decoding for Compositional Generalization in Language

What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation

Field-wise Learning for Multi-field Categorical Data

What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks

ContraGAN: Contrastive Learning for Conditional Image Generation

On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems

Understanding the Role of Training Regimes in Continual Learning

Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform

Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts

Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning

Neural Anisotropy Directions

Neural Power Units

Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

Fairness without Demographics through Adversarially Reweighted Learning

Scalable Belief Propagation via Relaxed Scheduling

Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming

Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine

PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

Manifold GPLVMs for discovering non-Euclidean latent structure in neural data

Off-Policy Evaluation and Learning for External Validity under a Covariate Shift

Improving Generalization in Reinforcement Learning with Mixture Regularization

Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems

A shooting formulation of deep learning

Breaking the Communication-Privacy-Accuracy Trilemma

Federated Accelerated Stochastic Gradient Descent

Advances in Black-Box VI: Normalizing Flows, Importance Weighting, and Optimization

Learning Manifold Implicitly via Explicit Heat-Kernel Learning

Do Adversarially Robust ImageNet Models Transfer Better?

Neural Sparse Voxel Fields

A Convolutional Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction

Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning

Hierarchical nucleation in deep neural networks

Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity

Model Selection for Production System via Automated Online Experiments

Batch normalization provably avoids ranks collapse for randomly initialised deep networks

Generalization bound of globally optimal non-convex neural network training: Transportation map estimation by infinite dimensional Langevin dynamics

SURF: A Simple, Universal, Robust, Fast Distribution Learning Algorithm

Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks

Adversarial Counterfactual Learning and Evaluation for Recommender System

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Learning with Operator-valued Kernels in Reproducing Kernel Krein Spaces

Differentiable Meta-Learning of Bandit Policies

Independent Policy Gradient Methods for Competitive Reinforcement Learning

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

Co-exposure Maximization in Online Social Networks

Predictive Information Accelerates Learning in RL

Group-Fair Online Allocation in Continuous Time

Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Distributions

Tight last-iterate convergence rates for no-regret learning in multi-player games

Inductive Quantum Embedding

Chaos, Extremism and Optimism: Volume Analysis of Learning in Games

A Statistical Framework for Low-bitwidth Training of Deep Neural Networks

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

Learning Guidance Rewards with Trajectory-space Smoothing

Learning Representations from Audio-Visual Spatial Alignment

Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization

Matrix Completion with Hierarchical Graph Side Information

On Regret with Multiple Best Arms

Delay and Cooperation in Nonstochastic Linear Bandits

Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs

A Limitation of the PAC-Bayes Framework

Implicit Distributional Reinforcement Learning

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough

Attribution Preservation in Network Compression for Reliable Network Interpretation

Neural Complexity Measures

Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge

Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model

Mutual exclusivity as a challenge for deep neural networks

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

Cross-lingual Retrieval for Iterative Self-Supervised Training

Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms

Continuous Meta-Learning without Tasks

FleXOR: Trainable Fractional Quantization

Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models

O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers

Adam with Bandit Sampling for Deep Learning

Using noise to probe recurrent neural network structure and prune synapses

Understanding Deep Architecture with Reasoning Layer

Worst-Case Analysis for Randomly Collected Data

Cooperative Heterogeneous Deep Reinforcement Learning

Random Reshuffling: Simple Analysis with Vast Improvements

A Novel Approach for Constrained Optimization in Graphical Models

Winning the Lottery with Continuous Sparsification

Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding

Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Proximal Mapping for Deep Regularization

ShiftAddNet: A Hardware-Inspired Deep Network

A Catalyst Framework for Minimax Optimization

A Computational Separation between Private Learning and Online Learning

Explainable Voting

Neural encoding with visual attention

Linear-Sample Learning of Low-Rank Distributions

Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks

Constrained episodic reinforcement learning in concave-convex and knapsack settings

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning

The Complete Lasso Tradeoff Diagram

Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks

Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction

Graph Contrastive Learning with Augmentations

Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes

ARMA Nets: Expanding Receptive Field for Dense Prediction

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks

GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs

Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

RandAugment: Practical Automated Data Augmentation with a Reduced Search Space

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization

First Order Constrained Optimization in Policy Space

Sinkhorn Barycenter via Functional Gradient Descent

Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees

Statistical Optimal Transport posed as Learning Kernel Embedding

Matrix Inference and Estimation in Multi-Layer Models

Pruning neural networks without any data by iteratively conserving synaptic flow

Offline Imitation Learning with a Misspecified Simulator

Training Stronger Baselines for Learning to Optimize

Sinkhorn Natural Gradient for Generative Models

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems

FedSplit: an algorithmic framework for fast federated optimization

Precise expressions for random projections: Low-rank approximation and randomized Newton

Modern Hopfield Networks and Attention for Immune Repertoire Classification

Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty

SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory

Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

Making Non-Stochastic Control (Almost) as Easy as Stochastic

Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method

An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch

Robust Multi-Agent Reinforcement Learning with Model Uncertainty

Differentially Private Clustering: Tight Approximation Ratios

FrugalML: How to use ML Prediction APIs more accurately and cheaply

Rethinking the Value of Labels for Improving Class-Imbalanced Learning

On Convergence and Generalization of Dropout Training

Counterfactual Prediction for Bundle Treatment

Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels

Measuring Robustness to Natural Distribution Shifts in Image Classification

Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient

Online Linear Optimization with Many Hints

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Hitting the High Notes: Subset Selection for Maximizing Expected Order Statistics

Demystifying Orthogonal Monte Carlo and Beyond

Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization

A Dynamical Central Limit Theorem for Shallow Neural Networks

Dual-Resolution Correspondence Networks

Near-Optimal Reinforcement Learning with Self-Play

An Unsupervised Information-Theoretic Perceptual Quality Metric

Exact expressions for double descent and implicit regularization via surrogate random design

Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference

Bayesian Attention Modules

Uncertainty Quantification for Inferring Hawkes Networks

Position-based Scaled Gradient for Model Quantization and Pruning

A Bayesian Perspective on Training Speed and Model Selection

Meta-Learning Requires Meta-Augmentation

Tensor Completion Made Practical

Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge

Learning Black-Box Attackers with Transferable Priors and Query Feedback

Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds

Estimating decision tree learnability with polylogarithmic sample complexity

Generalized Leverage Score Sampling for Neural Networks

On Reward-Free Reinforcement Learning with Linear Function Approximation

Causal Estimation with Functional Confounders

Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization

Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors

Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing

ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

On Adaptive Attacks to Adversarial Example Defenses

Universal guarantees for decision tree induction via a higher-order splitting criterion

Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification

Learning Structured Distributions From Untrusted Batches: Faster and Simpler

Distributed Newton Can Communicate Less and Resist Byzantine Workers

Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability

Identifying Learning Rules From Neural Network Observables

Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagation

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

Gradient-EM Bayesian Meta-Learning

BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning

Understanding and Exploring the Network with Stochastic Architectures

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

Causal Discovery in Physical Systems from Videos

Learning Compositional Rules via Neural Program Synthesis

Implicit Regularization and Convergence for Weight Normalization

Stage-wise Conservative Linear Bandits

Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes

Consistency Regularization for Certified Robustness of Smoothed Classifiers

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

Open Graph Benchmark: Datasets for Machine Learning on Graphs

Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks

Preference-based Reinforcement Learning with Finite-Time Guarantees

Predicting Training Time Without Training

Practical No-box Adversarial Attacks against DNNs

Neural Networks with Recurrent Generative Feedback

AViD Dataset: Anonymized Videos from Diverse Countries

How to Characterize The Landscape of Overparameterized Convolutional Neural Networks

Deep Direct Likelihood Knockoffs

Calibrated Reliable Regression using Maximum Mean Discrepancy

Instance-based Generalization in Reinforcement Learning

Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits

Community detection using fast low-cardinality semidefinite programming 

Randomized tests for high-dimensional regression: A more efficient and powerful solution

Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?

Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition

Robust Pre-Training by Adversarial Contrastive Learning

Asymptotically Optimal Exact Minibatch Metropolis-Hastings

Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations

Towards Better Generalization of Adaptive Gradient Methods

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Online Convex Optimization Over Erdos-Renyi Random Networks

Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

Sampling-Decomposable Generative Adversarial Recommender

Boundary thickness and robustness in learning models

Consistent Structural Relation Learning for Zero-Shot Segmentation

Statistical-Query Lower Bounds via Functional Gradients

Reward-rational (implicit) choice: A unifying formalism for reward learning

Partially View-aligned Clustering

How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

Succinct and Robust Multi-Agent Communication With Temporal Message Control

Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

Learning Utilities and Equilibria in Non-Truthful Auctions

Weston-Watkins Hinge Loss and Ordered Partitions

DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks

Personalized Federated Learning with Moreau Envelopes

Reciprocal Adversarial Learning via Characteristic Functions

AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning

Input-Aware Dynamic Backdoor Attack

Uncertainty Aware Semi-Supervised Learning on Graph Data

Generalised Bayesian Filtering via Sequential Monte Carlo

Optimizing Mode Connectivity via Neuron Alignment

Non-Stochastic Control with Bandit Feedback

A Biologically Plausible Neural Network for Slow Feature Analysis

AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

A Benchmark for Systematic Generalization in Grounded Language Understanding

A Game Theoretic Analysis of Additive Adversarial Attacks and Defenses

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

Marginal Utility for Planning in Continuous or Large Discrete Action Spaces

Learning Linear Programs from Optimal Decisions

Unsupervised Learning of Dense Visual Representations

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

Sparse Symplectically Integrated Neural Networks

Continual Learning of Control Primitives : Skill Discovery via Reset-Games

Distributionally Robust Federated Averaging

Learning by Minimizing the Sum of Ranked Range

From Boltzmann Machines to Neural Networks and Back Again

Efficient Learning of Discrete Graphical Models

MetaPoison: Practical General-purpose Clean-label Data Poisoning

BayReL: Bayesian Relational Learning for Multi-omics Data Integration

Why are Adaptive Methods Good for Attention Models?

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

Learning Optimal Representations with the Decodable Information Bottleneck

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

Fair Hierarchical Clustering

MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation

Program Synthesis with Pragmatic Communication

Sparse and Continuous Attention Mechanisms

TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search

Subgroup-based Rank-1 Lattice Quasi-Monte Carlo

Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows

Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps

Finite-Time Analysis for Double Q-learning

Adversarial robustness via robust low rank representations

Understanding Gradient Clipping in Private SGD: A Geometric Perspective

The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space

General Control Functions for Causal Effect Estimation from IVs

Large-Scale Methods for Distributionally Robust Optimization

Towards a Better Global Loss Landscape of GANs

Flexible mean field variational inference using mixtures of non-overlapping exponential families

A Fair Classifier Using Kernel Density Estimation

Sequential Bayesian Experimental Design with Variable Cost Structure

Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering

Barking up the right tree: an approach to search over molecule synthesis DAGs

Exemplar Guided Active Learning

Subgraph Neural Networks

Multi-Plane Program Induction with 3D Box Priors

X-CAL: Explicit Calibration for Survival Analysis

Smoothed Geometry for Robust Attribution

Interior Point Solving for LP-based prediction+optimisation

Privacy Amplification via Random Check-Ins

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

Dynamic Regret of Policy Optimization in Non-Stationary Environments

Learning Invariances in Neural Networks from Training Data

Geometric All-way Boolean Tensor Decomposition

Generalized Hindsight for Reinforcement Learning

Automatic Curriculum Learning through Value Disagreement

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Ensuring Fairness Beyond the Training Data

Reward Propagation Using Graph Convolutional Networks

Neurosymbolic Reinforcement Learning with Formally Verified Exploration

Learning to Select Best Forecast Tasks for Clinical Outcome Prediction

Fairness with Overlapping Groups; a Probabilistic Perspective

Generalization Bound of Gradient Descent for Non-Convex Metric Learning

Reconsidering Generative Objectives For Counterfactual Reasoning

Optimizing Neural Networks via Koopman Operator Theory

Predictive coding in balanced neural networks with noise, chaos and delays

Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control

Adversarial Blocking Bandits

Inference for Batched Bandits

Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects

Markovian Score Climbing: Variational Inference with KL(p||q)

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

Rethinking Pre-training and Self-training

Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons

The Generalization-Stability Tradeoff In Neural Network Pruning

Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights

The Cone of Silence: Speech Separation by Localization

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms

Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery

Learning Physical Graph Representations from Visual Scenes

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval

Why Normalizing Flows Fail to Detect Out-of-Distribution Data

Demixed shared component analysis of neural population data from multiple brain areas

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?

Constant-Expansion Suffices for Compressed Sensing with Generative Priors

Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis

Pointer Graph Networks

Thunder: a Fast Coordinate Selection Solver for Sparse Learning

MOPO: Model-based Offline Policy Optimization

Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing

From Predictions to Decisions: Using Lookahead Regularization

Robust Federated Learning: The Case of Affine Distribution Shifts

Learning the Geometry of Wave-Based Imaging

Random Reshuffling is Not Always Better

Learning Composable Energy Surrogates for PDE Order Reduction

COBE: Contextualized Object Embeddings from Narrated Instructional Video

Optimal Learning from Verified Training Data

Counterexample-Guided Learning of Monotonic Neural Networks

Toward the Fundamental Limits of Imitation Learning

Targeted Adversarial Perturbations for Monocular Depth Prediction

Supermasks in Superposition

Online Agnostic Boosting via Regret Minimization

Differentiable Causal Discovery from Interventional Data

Truncated Linear Regression in High Dimensions

Design Space for Graph Neural Networks

Adversarial Example Games

WoodFisher: Efficient Second-Order Approximation for Neural Network Compression

Differentiable Augmentation for Data-Efficient GAN Training

Taming Discrete Integration via the Boon of Dimensionality

On the Theory of Transfer Learning: The Importance of Task Diversity

Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE

Agnostic Learning of a Single Neuron with Gradient Descent

Coded Sequential Matrix Multiplication For Straggler Mitigation

Depth Uncertainty in Neural Networks

Fast Matrix Square Roots with Applications to Gaussian Processes and Bayesian Optimization

Interpretable multi-timescale models for predicting fMRI responses to continuous natural speech

Simple and Scalable Sparse k-means Clustering via Feature Ranking

Strictly Batch Imitation Learning by Energy-based Distribution Matching

Off-Policy Evaluation via the Regularized Lagrangian

Online Non-Convex Optimization with Imperfect Feedback

Identifying Mislabeled Data using the Area Under the Margin Ranking

See, Hear, Explore: Curiosity via Audio-Visual Association

Probabilistic Fair Clustering

Byzantine Resilient Distributed Multi-Task Learning

Geometric Exploration for Online Control

Autofocused oracles for model-based design

EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs

Differentiable Top-k with Optimal Transport

Reinforcement Learning with Augmented Data

Factorizable Graph Convolutional Networks

Handling Missing Data with Graph Representation Learning

Online Bayesian Persuasion

Graphon Neural Networks and the Transferability of Graph Neural Networks

Linearly Converging Error Compensated SGD

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them

Efficient Contextual Bandits with Continuous Actions

From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

Smoothed Analysis of Online and Differentially Private Learning

Learning Rich Rankings

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning

Investigating Gender Bias in Language Models Using Causal Mediation Analysis

Calibration of Shared Equilibria in General Sum Partially Observable Markov Games

Statistical Guarantees of Distributed Nearest Neighbor Classification

Learning Differentiable Programs with Admissible Neural Heuristics

Learning Certified Individually Fair Representations

Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization

Debiasing Averaged Stochastic Gradient Descent to handle missing values

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Learning from Mixtures of Private and Public Populations

Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations

Information theoretic limits of learning a sparse rule

Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee

Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice

Principal Neighbourhood Aggregation for Graph Nets

Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes

Look-ahead Meta Learning for Continual Learning

Movement Pruning: Adaptive Sparsity by Fine-Tuning

Fourier Sparse Leverage Scores and Approximate Kernel Learning

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

Learning to Incentivize Other Learning Agents

Improved Techniques for Training Score-Based Generative Models

Learning Affordance Landscapes for Interaction Exploration in 3D Environments

Debugging Tests for Model Explanations

Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters

UCLID-Net: Single View Reconstruction in Object Space

Exploiting weakly supervised visual patterns to learn from partial annotations

Can Temporal-Diﬀerence and Q-Learning Learn Representation? A Mean-Field Theory

GradAug: A New Regularization Method for Deep Neural Networks

Reducing Adversarially Robust Learning to Non-Robust PAC Learning

Online Bayesian Goal Inference for Boundedly Rational Planning Agents

A Robust Functional EM Algorithm for Incomplete Panel Count Data

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow

RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor

Walking in the Shadow: A New Perspective on Descent Directions for Constrained Minimization

Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice

Sharp uniform convergence bounds through empirical centralization

Efficient Generation of Structured Objects with Constrained Adversarial Networks

Disentangling by Subspace Diffusion

Value-driven Hindsight Modelling

Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion

Regression with reject option and application to kNN

A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods

Deep Statistical Solvers

POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis

Dynamic allocation of limited memory resources in reinforcement learning

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

A Topological Filter for Learning with Label Noise

Node Embeddings and Exact Low-Rank Representations of Complex Networks

Hyperparameter Ensembles for Robustness and Uncertainty Quantification

Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment

Faithful Embeddings for Knowledge Base Queries

The interplay between randomness and structure during learning in RNNs

Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization

On Efficiency in Hierarchical Reinforcement Learning

Cross-validation Confidence Intervals for Test Error

Learning Graph Structure With A Finite-State Automaton Layer

Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach

Continuous Submodular Maximization: Beyond DR-Submodularity

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs

Joint Contrastive Learning with Infinite Possibilities

Gradient Estimation with Stochastic Softmax Tricks

Leveraging Predictions in Smoothed Online Convex Optimization via Gradient-based Algorithms

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding

An operator view of policy gradient methods

Contextual Reserve Price Optimization in Auctions via Mixed Integer Programming

Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning

UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

CoinDICE: Off-Policy Confidence Interval Estimation

Learning Latent Space Energy-Based Prior Model

Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation

On the Modularity of Hypernetworks

On Uniform Convergence and Low-Norm Interpolation Learning

Sufficient dimension reduction for classification using principal optimal transport direction

Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs

Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability

List-Decodable Mean Estimation via Iterative Multi-Filtering

Distributionally Robust Local Non-parametric Conditional Estimation

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits

Better Set Representations For Relational Reasoning

Decision trees as partitioning machines to characterize their generalization properties

Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

Color Visual Illusions: A Statistics-based Computational Model

Online Learning with Primary and Secondary Losses

Learning with Differentiable Pertubed Optimizers

MRI Banding Removal via Adversarial Training

Distributed Distillation for On-Device Learning

Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes

Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification

Self-Supervised Few-Shot Learning on Point Clouds

Approximate Cross-Validation for Structured Models

An Efficient Framework for Clustered Federated Learning

Gaussian Gated Linear Networks

3D Shape Reconstruction from Vision and Touch

Soft Contrastive Learning for Visual Localization

Online Robust Regression via SGD on the l1 loss

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

A Causal View on Robustness of Neural Networks

Listening to Sounds of Silence for Speech Denoising

The NetHack Learning Environment

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

Multi-Task Reinforcement Learning with Soft Modularization

Causal Imitation Learning With Unobserved Confounders

CSER: Communication-efficient SGD with Error Reset

The All-or-Nothing Phenomenon in Sparse Tensor PCA

Cooperative Multi-player Bandit Optimization

Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs

The phase diagram of approximation rates for deep neural networks

Deep Automodulators

Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning

The Statistical Cost of Robust Kernel Hyperparameter Turning

Choice Bandits

Reinforcement Learning with Feedback Graphs

Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel

Dynamic Fusion of Eye Movement Data and Verbal Narrations in Knowledge-rich Domains

On Second Order Behaviour in Augmented Neural ODEs

Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views

Regret in Online Recommendation Systems

An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

The Devil is in the Detail: A Framework for Macroscopic Prediction via Microscopic Models

Can Graph Neural Networks Count Substructures?

Ode to an ODE

Approximate Cross-Validation with Low-Rank Data in High Dimensions

Online Multitask Learning with Long-Term Memory

Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning

CHIP: A Hawkes Process Model for Continuous-time Networks with Scalable and Consistent Estimation

Unsupervised Translation of Programming Languages

Conic Descent and its Application to Memory-efficient Optimization over Positive Semidefinite Matrices

STEER : Simple Temporal Regularization For Neural ODE

Certifying Strategyproof Auction Networks

A Spectral Energy Distance for Parallel Speech Synthesis

Distributionally Robust Parametric Maximum Likelihood Estimation

Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

Building powerful and equivariant graph neural networks with structural message-passing

Meta-trained agents implement Bayes-optimal agents

Compositional Visual Generation with Energy Based Models

Task-agnostic Exploration in Reinforcement Learning

Empirical Likelihood for Contextual Bandits

Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning

AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning

Metric-Free Individual Fairness in Online Learning

Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis

Deep Inverse Q-learning with Constraints

Compact task representations as a normative model for higher-order brain activity

Fast Transformers with Clustered Attention

Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree

Fully Dynamic Algorithm for Constrained Submodular Optimization

Stochastic Stein Discrepancies

Unfolding recurrence by Green’s functions for optimized reservoir computing

Guiding Deep Molecular Optimization with Genetic Exploration

Steering Distortions to Preserve Classes and Neighbors in Supervised Dimensionality Reduction

Debiased Contrastive Learning

An analytic theory of shallow networks dynamics for hinge loss classification

Classification with Valid and Adaptive Coverage

High-Throughput Synchronous Deep RL

Consistent feature selection for analytic deep neural networks

OrganITE: Optimal transplant donor organ offering using an individual treatment effect

On 1/n neural representation and robustness

A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

A simple normative network approximates local non-Hebbian learning in the cortex

Boosting Adversarial Training with Hypersphere Embedding

Robust Sequence Submodular Maximization

Improving Policy-Constrained Kidney Exchange via Pre-Screening

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Estimating Training Data Influence by Tracing Gradient Descent

MCUNet: Tiny Deep Learning on IoT Devices

Bi-level Score Matching for Learning Energy-based Latent Variable Models

Training Linear Finite-State Machines

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations

PAC-Bayesian Bound for the Conditional Value at Risk

Neuron Shapley: Discovering the Responsible Neurons

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining

Adversarial Robustness of Supervised Sparse Coding

Efficient Learning of Generative Models via Finite-Difference Score Matching

CLEARER: Multi-Scale Neural Architecture Search for Image Restoration

Graph Meta Learning via Local Subgraphs

Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization

Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

Digraph Inception Convolutional Networks

Learning Disentangled Representations of Videos with Missing Data

Graph Random Neural Networks for Semi-Supervised Learning on Graphs

Smoothly Bounding User Contributions in Differential Privacy

Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

Zero-Resource Knowledge-Grounded Dialogue Generation

Contrastive Learning with Adversarial Examples

Sub-sampling for Efficient Non-Parametric Bandit Exploration

Language and Visual Entity Relationship Graph for Agent Navigation

A Combinatorial Perspective on Transfer Learning

Learning Robust Decision Policies from Observational Data

Neuron Merging: Compensating for Pruned Neurons

Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations

Constraining Variational Inference with Geometric Jensen-Shannon Divergence

Adversarial Learning for Robust Deep Clustering

Biological credit assignment through dynamic inversion of feedforward networks

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

Neural Networks Learning and Memorization with (almost) no Over-Parameterization

Phase retrieval in high dimensions: Statistical and computational phase transitions

From Finite to Countable-Armed Bandits

A Variational Approach for Learning from Positive and Unlabeled Data

Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders

GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network

Latent Dynamic Factor Analysis of High-Dimensional Neural Recordings

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning

Synthesizing Tasks for Block-based Programming

Neutralizing Self-Selection Bias in Sampling for Sortition

Learning Semantic-aware Normalization for Generative Adversarial Networks

Causal analysis of Covid-19 Spread in Germany

Posterior Re-calibration for Imbalanced Datasets

Optimally Deceiving a Learning Leader in Stackelberg Games

Regularizing Black-box Models for Improved Interpretability

Model-based Policy Optimization with Unsupervised Model Adaptation

GANSpace: Discovering Interpretable GAN Controls

Effective Diversity in Population Based Reinforcement Learning

Learning Invariants through Soft Unification

Multi-Stage Influence Function

On ranking via sorting by estimated expected utility

Algorithmic recourse under imperfect causal knowledge: a probabilistic approach

Locally-Adaptive Nonparametric Online Learning

Small Nash Equilibrium Certificates in Very Large Games

Influence-Augmented Online Planning for Complex Environments

Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework

Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian

Dynamic Submodular Maximization

Discovering Reinforcement Learning Algorithms

Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations

VarGrad: A Low-Variance Gradient Estimator for Variational Inference

Online Decision Based Visual Tracking via Reinforcement Learning

Stationary Activations for Uncertainty Calibration in Deep Learning

NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity

How hard is to distinguish graphs with graph neural networks?

On Testing of Samplers

Towards Scalable Bayesian Learning of Causal DAGs

Variational Interaction Information Maximization for Cross-domain Disentanglement

Synthetic Data Generators -- Sequential and Private

The Convolution Exponential and Generalized Sylvester Flows

When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes

Rational neural networks

Non-Crossing Quantile Regression for Distributional Reinforcement Learning

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning

Real World Games Look Like Spinning Tops

Fast Fourier Convolution

Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space

Stochastic Optimization for Performative Prediction

A Self-Tuning Actor-Critic Algorithm

A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

Restoring Negative Information in Few-Shot Object Detection

Graph Stochastic Neural Networks for Semi-supervised Learning

BoxE: A Box Embedding Model for Knowledge Base Completion

Decentralized Accelerated Proximal Gradient Descent

Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking

Munchausen Reinforcement Learning

Hierarchical Neural Architecture Search for Deep Stereo Matching

Time-Reversal Symmetric ODE Network

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study

CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection

Learning Parities with Neural Networks

Quantile Propagation for Wasserstein-Approximate Gaussian Processes

The Implications of Local Correlation on Learning Some Deep Functions

Deep Shells: Unsupervised Shape Correspondence with Optimal Transport

A Theoretical Framework for Target Propagation

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits

Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation

Efficient Clustering Based On A Unified View Of K-means And Ratio-cut

Reservoir Computing meets Recurrent Kernels and Structured Transforms

SuperLoss: A Generic Loss for Robust Curriculum Learning

Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation

Lower Bounds and Optimal Algorithms for Personalized Federated Learning

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Spike and slab variational Bayes for high dimensional logistic regression

Linear Disentangled Representations and Unsupervised Action Estimation

Interventional Few-Shot Learning

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

A Randomized Algorithm to Reduce the Support of Discrete Measures

BRP-NAS: Prediction-based NAS using GCNs

Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering

Meta-Consolidation for Continual Learning

Learning from Aggregate Observations

Smooth And Consistent Probabilistic Regression Trees

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods

CASTLE: Regularization via Auxiliary Causal Graph Discovery

Prediction with Corrupted Expert Advice

Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality

Model Inversion Networks for Model-Based Optimization

Universal Function Approximation on Graphs

Efficient active learning of sparse halfspaces with arbitrary bounded noise

On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method

MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models

Provably Efficient Neural GTD for Off-Policy Learning

Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

Probabilistic Circuits for Variational Inference in Discrete Graphical Models

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization

Falcon: Fast Spectral Inference on Encrypted Data

Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation

Self-training Avoids Using Spurious Features Under Domain Shift

Model-based Adversarial Meta-Reinforcement Learning

An implicit function learning approach for parametric modal regression

Online Optimization with Memory and Competitive Control

Automatically Learning Compact Quality-aware Surrogates for Optimization Problems

Hierarchical Granularity Transfer Learning

Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data

Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards

Bayesian Multi-type Mean Field Multi-agent Imitation Learning

MomentumRNN: Integrating Momentum into Recurrent Neural Networks

Optimal Query Complexity of Secure Stochastic Convex Optimization

Self-Distillation as Instance-Specific Label Smoothing

Diversity can be Transferred: Output Diversification for White- and Black-box Attacks

Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information

On Adaptive Distance Estimation

The Power of Comparisons for Actively Learning Linear Classifiers

Multi-Fidelity Bayesian Optimization via Deep Neural Networks

The route to chaos in routing games: When is price of anarchy too optimistic?

Intra-Processing Methods for Debiasing Neural Networks

Entrywise convergence of iterative methods for eigenproblems

SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds

Learning Strategy-Aware Linear Classifiers

Functional Regularization for Representation Learning: A Unified Theoretical Perspective

Learning Sparse Prototypes for Text Generation

Towards a Combinatorial Characterization of Bounded-Memory Learning

RepPoints v2: Verification Meets Regression for Object Detection

Submodular Meta-Learning

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification

Detecting Interactions from Neural Networks via Topological Analysis

Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time

Learning to Mutate with Hypergradient Guided Population

Network size and size of the weights in memorization with two-layers neural networks

COPT: Coordinated Optimal Transport on Graphs

Deep Imitation Learning for Bimanual Robotic Manipulation

Improving Auto-Augment via Augmentation-Wise Weight Sharing

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation

Rotated Binary Neural Network

Sense and Sensitivity Analysis: Simple Post-Hoc Analysis of Bias Due to Unobserved Confounding

Wasserstein Distances for Stereo Disparity Estimation

Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

Security Analysis of Safe and Seldonian Reinforcement Learning Algorithms

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Provably Robust Metric Learning

Estimation of Skill Distribution from a Tournament

Ultra-Low Precision 4-bit Training of Deep Neural Networks

Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension

Shared Space Transfer Learning for analyzing multi-site fMRI data

Planning with General Objective Functions: Going Beyond Total Rewards

Structured Prediction for Conditional Meta-Learning

Correlation Robust Influence Maximization

Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time

MOReL: Model-Based Offline Reinforcement Learning

GCN meets GPU: Decoupling “When to Sample” from “How to Sample”

NVAE: A Deep Hierarchical Variational Autoencoder

VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain

Zap Q-Learning With Nonlinear Function Approximation

Learning Deep Attribution Priors Based On Prior Knowledge

Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling

Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond

Neural Dynamic Policies for End-to-End Sensorimotor Learning

Sparse Graphical Memory for Robust Planning

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods

Weakly-Supervised Reinforcement Learning for Controllable Behavior

Modeling and Optimization Trade-off in Meta-learning

Structured Convolutions for Efficient Neural Network Design

Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning

Walsh-Hadamard Variational Inference for Bayesian Deep Learning

Efficient Algorithms for Device Placement of DNN Graph Operators

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings

Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration

The MAGICAL Benchmark for Robust Imitation

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

No-regret Learning in Price Competitions under Consumer Reference Effects

Self-Imitation Learning via Generalized Lower Bound Q-learning

Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding

Learning Agent Representations for Ice Hockey

Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks

On Numerosity of Deep Neural Networks

A mathematical theory of cooperative communication

Detection as Regression: Certified Object Detection with Median Smoothing

Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games

Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients

Improving Neural Network Training in Low Dimensional Random Bases

Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data

COT-GAN: Generating Sequential Data via Causal Optimal Transport

Learning from Label Proportions: A Mutual Contamination Framework

Truthful Data Acquisition via Peer Prediction

A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions

On the Equivalence between Online and Private Learnability beyond Binary Classification

Unsupervised Data Augmentation for Consistency Training

Hedging in games: Faster convergence of external and swap regrets

Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

What Makes for Good Views for Contrastive Learning?

Fairness in Streaming Submodular Maximization: Algorithms and Hardness

On Learning Ising Models under Huber's Contamination Model

Make One-Shot Video Object Segmentation Efficient Again

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

Fine-Grained Dynamic Head for Object Detection

Estimation and Imputation in Probabilistic Principal Component Analysis with Missing Not At Random Data

Meta-Learning through Hebbian Plasticity in Random Networks

Hold me tight! Influence of discriminative features on deep network boundaries

Heavy-tailed Representations, Text Polarity Classification & Data Augmentation

Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology

A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs

Efficient Low Rank Gaussian Variational Inference for Neural Networks

Learning Mutational Semantics

RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning

Bayesian Optimization for Iterative Learning

Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model

f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning

On the Role of Sparsity and DAG Constraints for Learning Linear DAGs

One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

Revisiting Frank-Wolfe for Polytopes: Strict Complementarity and Sparsity

Towards Neural Programming Interfaces

Transductive Information Maximization for Few-Shot Learning

A Bayesian Nonparametrics View into Deep Representations

Dynamic Regret of Convex and Smooth Functions

Unbalanced Sobolev Descent

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

Untangling tradeoffs between recurrence and self-attention in artificial neural networks

Exact Recovery of Mangled Clusters with Same-Cluster Queries

Woodbury Transformations for Deep Generative Flows

Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample

Self-Supervised MultiModal Versatile Networks

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

Neuron-level Structured Pruning using Polarization Regularizer

Bayesian Deep Learning and a Probabilistic Perspective of Generalization

Unsupervised object-centric video generation and decomposition in 3D

DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs

Natural Graph Networks

Causal Intervention for Weakly-Supervised Semantic Segmentation

Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies

Adversarial Sparse Transformer for Time Series Forecasting

Deep Structural Causal Models for Tractable Counterfactual Inference

Improved Algorithms for Convex-Concave Minimax Optimization

A Loss Function for Generative Neural Networks Based on Watson’s Perceptual Model

Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning

Neural Star Domain as Primitive Representation

Dirichlet Graph Variational Autoencoder

Parabolic Approximation Line Search for DNNs

Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms

GAIT-prop: A biologically plausible learning rule derived from backpropagation of error

Lipschitz-Certifiable Training with a Tight Outer Bound

Adaptive Sampling for Stochastic Risk-Averse Learning

Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions

Federated Bayesian Optimization via Thompson Sampling

Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed Form

Revisiting Parameter Sharing for Automatic Neural Channel Number Search

Self-Paced Deep Reinforcement Learning

An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

High-Fidelity Generative Image Compression

Online Influence Maximization under Linear Threshold Model

Impossibility Results for Grammar-Compressed Linear Algebra

Inverse Learning of Symmetries

Multi-task Causal Learning with Gaussian Processes

Finite Continuum-Armed Bandits

Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties

Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

Training Generative Adversarial Networks with Limited Data

Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations

Escaping Saddle-Point Faster under Interpolation-like Conditions

Self-Supervised Relational Reasoning for Representation Learning

Noise-Contrastive Estimation for Multivariate Point Processes

AutoBSS: An Efficient Algorithm for Block Stacking Style Search

Data Diversification: A Simple Strategy For Neural Machine Translation

Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization

POMO: Policy Optimization with Multiple Optima for Reinforcement Learning

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces

Energy-based Out-of-distribution Detection

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers

Self-Supervised Visual Representation Learning from Hierarchical Grouping

CircleGAN: Generative Adversarial Learning across Spherical Circles