Workshop
NeurIPS 2022 Workshop on Score-Based Methods
Yingzhen Li · Yang Song · Valentin De Bortoli · Francois-Xavier Briol · Wenbo Gong · Alexia Jolicoeur-Martineau · Arash Vahdat
Room 293 - 294
Fri 2 Dec, 6:50 a.m. PST
The score function, which is the gradient of the log-density, provides a unique way to represent probability distributions. By working with distributions through score functions, researchers have been able to develop efficient tools for machine learning and statistics, collectively known as score-based methods.
Score-based methods have had a significant impact on vastly disjointed subfields of machine learning and statistics, such as generative modeling, Bayesian inference, hypothesis testing, control variates and Stein’s methods. For example, score-based generative models, or denoising diffusion models, have emerged as the state-of-the-art technique for generating high quality and diverse images. In addition, recent developments in Stein’s method and score-based approaches for stochastic differential equations (SDEs) have contributed to the developement of fast and robust Bayesian posterior inference in high dimensions. These have potential applications in engineering fields, where they could help improve simulation models.
At our workshop, we will bring together researchers from these various subfields to discuss the success of score-based methods, and identify common challenges across different research areas. We will also explore the potential for applying score-based methods to even more real-world applications, including in computer vision, signal processing, and computational chemistry. By doing so, we hope to folster collaboration among researchers and build a more cohesive research community focused on score-based methods.
Schedule
Fri 6:50 a.m. - 7:00 a.m.
|
Introduction and opening remarks
(
Introduction
)
>
SlidesLive Video |
🔗 |
Fri 7:00 a.m. - 7:30 a.m.
|
Invited talk: Karsten Kreis
(
Talk
)
>
SlidesLive Video |
Karsten Kreis 🔗 |
Fri 7:30 a.m. - 8:00 a.m.
|
Invited Talk: Tommi Jaakkola
(
Talk
)
>
SlidesLive Video |
Tommi Jaakkola 🔗 |
Fri 8:00 a.m. - 9:00 a.m.
|
Poster session 1
(
Poster
)
>
|
Yingzhen Li 🔗 |
Fri 9:00 a.m. - 10:00 a.m.
|
Panel discussion
(
Discussion Panel
)
>
SlidesLive Video |
🔗 |
Fri 10:00 a.m. - 10:30 a.m.
|
Contributed talk session 1
(
talk
)
>
SlidesLive Video |
🔗 |
Fri 10:30 a.m. - 11:30 a.m.
|
lunch break
|
🔗 |
Fri 11:30 a.m. - 12:00 p.m.
|
Invited Talk: Guan-Horng Liu
(
Talk
)
>
SlidesLive Video |
Guan-Horng Liu 🔗 |
Fri 12:00 p.m. - 12:30 p.m.
|
Invited Talk: Tamara Fernandez
(
Talk
)
>
SlidesLive Video |
Tamara Fernandez 🔗 |
Fri 12:30 p.m. - 1:00 p.m.
|
Contributed talk session 2
(
talk
)
>
SlidesLive Video |
🔗 |
Fri 1:00 p.m. - 2:00 p.m.
|
Poster session 2
(
poster
)
>
|
🔗 |
Fri 2:00 p.m. - 2:30 p.m.
|
Invited Talk: Chenlin Meng
(
Talk
)
>
SlidesLive Video |
Chenlin Meng 🔗 |
Fri 2:30 p.m. - 3:00 p.m.
|
Invited Talk: Mohammad Norouzi
(
Talk
)
>
SlidesLive Video |
Mohammad Norouzi 🔗 |
-
|
Modeling Temporal Data as Continuous Functions with Process Diffusion ( Poster ) > link | Marin Biloš · Kashif Rasul · Anderson Schneider · Yuriy Nevmyvaka · Stephan Günnemann 🔗 |
-
|
Self-Guided Diffusion Model ( Poster ) > link | TAO HU · David Zhang · Yuki Asano · Gertjan Burghouts · Cees Snoek 🔗 |
-
|
Locking and Quacking: Stacking Bayesian models predictions by log-pooling and superposition ( Poster ) > link | Yuling Yao · Luiz Carvalho · Diego Mesquita 🔗 |
-
|
Action Matching: A Variational Method for Learning Stochastic Dynamics from Samples ( Poster ) > link | Kirill Neklyudov · Daniel Severo · Alireza Makhzani 🔗 |
-
|
Likelihood Score under Generalized Self-Concordance ( Poster ) > link | Lang Liu · Zaid Harchaoui 🔗 |
-
|
Noise-conditional Maximum Likelihood Estimation with Score-based Sampling ( Poster ) > link | Henry Li · Yuval Kluger 🔗 |
-
|
Journey to the BAOAB-limit: finding effective MCMC samplers for score-based models ( Poster ) > link | Ajay Jain · Ben Poole 🔗 |
-
|
First hitting diffusion models ( Poster ) > link | Mao Ye · Lemeng Wu · Qiang Liu 🔗 |
-
|
Score-based generative model learnmanifold-like structures with constrained mixing ( Poster ) > link | Li Kevin Wenliang · Ben Moran 🔗 |
-
|
Exploring the Design Space of Generative Diffusion Processes for Sparse Graphs ( Poster ) > link | Pierre-André Noël · Pau Rodriguez 🔗 |
-
|
Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning ( Poster ) > link | Souradip Chakraborty · Amrit Bedi · Alec Koppel · Furong Huang · Pratap Tokekar · Dinesh Manocha 🔗 |
-
|
Unsupervised Controllable Generation with Score-based Diffusion Models: Disentangled Latent Code Guidance ( Poster ) > link | Yeongmin Kim · Dongjun Kim · Hyeonmin Lee · Il-chul Moon 🔗 |
-
|
Molecular Docking with Diffusion Generative Models ( Oral ) > link | Gabriele Corso · Hannes Stärk · Bowen Jing · Regina Barzilay · Tommi Jaakkola 🔗 |
-
|
Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models ( Poster ) > link | Vikram Voleti · Chris Pal · Adam Oberman 🔗 |
-
|
Statistical Efficiency of Score Matching: The View from Isoperimetry ( Oral ) > link | Frederic Koehler · Alexander Heckett · Andrej Risteski 🔗 |
-
|
Score-Based Generative Models with Lévy Processes ( Poster ) > link | Eunbi Yoon · Keehun Park · Jinhyeok Kim · Sungbin Lim 🔗 |
-
|
Fast Sampling of Diffusion Models via Operator Learning ( Poster ) > link | Hongkai Zheng · Weili Nie · Arash Vahdat · Kamyar Azizzadenesheli · Anima Anandkumar 🔗 |
-
|
Score Modeling for Simulation-based Inference ( Poster ) > link | Tomas Geffner · George Papamakarios · Andriy Mnih 🔗 |
-
|
Improving Conditional Score-Based Generation with Calibrated Classification and Joint Training ( Poster ) > link | Paul K. Huang · Si-An Chen · Hsuan-Tien Lin 🔗 |
-
|
Dimension reduction via score ratio matching ( Poster ) > link | Michael Brennan · Ricardo Baptista · Youssef Marzouk 🔗 |
-
|
Spectral Diffusion Processes ( Poster ) > link | Angus Phillips · Thomas Seror · Michael Hutchinson · Valentin De Bortoli · Arnaud Doucet · Emile Mathieu 🔗 |
-
|
Convergence of score-based generative modeling for general data distributions ( Poster ) > link | Holden Lee · Jianfeng Lu · Yixin Tan 🔗 |
-
|
A generic diffusion-based approach for 3D human pose prediction in the wild ( Poster ) > link | Saeed Saadatnejad · Ali Rasekh · Mohammadreza Mofayezi · Yasamin Medghalchi · Sara Rajabzadeh · Taylor Mordan · Alexandre Alahi 🔗 |
-
|
Diffusion Models for Video Prediction and Infilling ( Poster ) > link | Tobias Höppe · Arash Mehrjou · Stefan Bauer · Didrik Nielsen · Andrea Dittadi 🔗 |
-
|
Discovering the Hidden Vocabulary of DALLE-2 ( Poster ) > link | Giannis Daras · Alex Dimakis 🔗 |
-
|
Multiresolution Textual Inversion ( Oral ) > link | Giannis Daras · Alex Dimakis 🔗 |
-
|
Neural Volumetric Mesh Generator ( Poster ) > link | Yan Zheng · Lemeng Wu · Xingchao Liu · Zhen Chen · Qiang Liu · Qixing Huang 🔗 |
-
|
Targeted Separation and Convergence with Kernel Discrepancies ( Oral ) > link | Alessandro Barp · Carl-Johann Simon-Gabriel · Mark Girolami · Lester Mackey 🔗 |
-
|
Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy ( Poster ) > link | Xing Liu · Andrew Duncan · Axel Gandy 🔗 |
-
|
Regularizing Score-based Models with Score Fokker-Planck Equations ( Poster ) > link | Chieh-Hsin Lai · Yuhta Takida · Naoki Murata · Toshimitsu Uesaka · Yuki Mitsufuji · Stefano Ermon 🔗 |
-
|
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions ( Poster ) > link | Sitan Chen · Sinho Chewi · Jerry Li · Yuanzhi Li · Adil Salim · Anru Zhang 🔗 |
-
|
Fast Sampling of Diffusion Models with Exponential Integrator ( Poster ) > link | Qinsheng Zhang · Yongxin Chen 🔗 |
-
|
On Distillation of Guided Diffusion Models ( Oral ) > link | Chenlin Meng · Ruiqi Gao · Diederik Kingma · Stefano Ermon · Jonathan Ho · Tim Salimans 🔗 |
-
|
An optimal control perspective on diffusion-based generative modeling ( Oral ) > link | Julius Berner · Lorenz Richter · Karen Ullrich 🔗 |
-
|
Conditioned Score-Based Models for Learning Collision-Free Trajectory Generation ( Poster ) > link | Joao Carvalho · Mark Baierl · Julen Urain · Jan Peters 🔗 |
-
|
Convergence in KL and Rényi Divergence of the Unadjusted Langevin Algorithm Using Estimated Score ( Poster ) > link | Kaylee Y. Yang · Andre Wibisono 🔗 |
-
|
On RKHS Choices for Assessing Graph Generators via Kernel Stein Statistics ( Poster ) > link | Wenkai Xu · Gesine D Reinert · Moritz Weckbecker 🔗 |
-
|
Proposal of a Score Based Approach to Sampling Using Monte Carlo Estimation of Score and Oracle Access to Target Density ( Poster ) > link | Curtis McDonald · Andrew Barron 🔗 |
-
|
Diffusion Prior for Online Decision Making: A Case Study of Thompson Sampling ( Poster ) > link | Yu-Guan Hsieh · Shiva Kasiviswanathan · Branislav Kveton · Patrick Blöbaum 🔗 |
-
|
Scalable Causal Discovery with Score Matching ( Poster ) > link | Francesco Montagna · Nicoletta Noceti · Lorenzo Rosasco · Kun Zhang · Francesco Locatello 🔗 |
-
|
All are Worth Words: a ViT Backbone for Score-based Diffusion Models ( Poster ) > link | Fan Bao · Chongxuan LI · Yue Cao · Jun Zhu 🔗 |
-
|
Fine-tuning Diffusion Models with Limited Data ( Poster ) > link | Taehong Moon · Moonseok Choi · Gayoung Lee · Jung-Woo Ha · Juho Lee 🔗 |
-
|
JPEG Artifact Correction using Denoising Diffusion Restoration Models ( Poster ) > link | Bahjat Kawar · Jiaming Song · Stefano Ermon · Michael Elad 🔗 |
-
|
Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation ( Poster ) > link | Han Huang · Leilei Sun · Bowen Du · Weifeng Lv 🔗 |
-
|
Denoising Diffusion for Sampling SAT Solutions ( Poster ) > link | Karlis Freivalds · Sergejs Kozlovičs 🔗 |
-
|
When are equilibrium networks scoring algorithms? ( Poster ) > link | Russell Tsuchida · Cheng Soon Ong 🔗 |
-
|
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow ( Poster ) > link | Xingchao Liu · Chengyue Gong · Qiang Liu 🔗 |
-
|
Let us Build Bridges: Understanding and Extending Diffusion Generative Models ( Poster ) > link | Xingchao Liu · Lemeng Wu · Mao Ye · Qiang Liu 🔗 |
-
|
Improved Marginal Unbiased Score Expansion (MUSE) via Implicit Differentiation ( Poster ) > link | Marius Millea 🔗 |
-
|
Few-Shot Diffusion Models ( Poster ) > link | Giorgio Giannone · Didrik Nielsen · Ole Winther 🔗 |
-
|
Batch Denoising via Blahut-Arimoto ( Poster ) > link | Qing Li · Cyril Guyot 🔗 |
-
|
Why Are Conditional Generative Models Better Than Unconditional Ones? ( Poster ) > link | Fan Bao · Chongxuan LI · Jiacheng Sun · Jun Zhu 🔗 |
-
|
Particle-based Variational Inference with Preconditioned Functional Gradient Flow ( Poster ) > link | Hanze Dong · Xi Wang · Yong Lin · Tong Zhang 🔗 |
-
|
Making Text-to-Image Diffusion Models Zero-Shot Image-to-Image Editors by Inferring "Random Seeds" ( Poster ) > link | Chen Henry Wu · Fernando D De la Torre 🔗 |
-
|
Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis ( Poster ) > link | Sangyun Lee · Hyungjin Chung · Jaehyeon Kim · Jong Chul Ye 🔗 |
-
|
Towards Healing the Blindness of Score Matching ( Poster ) > link | Mingtian Zhang · Oscar Key · Peter Hayes · David Barber · Brooks Paige · Francois-Xavier Briol 🔗 |