Mon 9:00 a.m. - 9:10 a.m.
|
Opening remarks
(
Talk
)
>
SlidesLive Video
|
Shiori Sagawa
🔗
|
Mon 9:10 a.m. - 9:35 a.m.
|
Distribution Shifts in AI for Social Good
(
Invited talk
)
>
SlidesLive Video
|
Ernest Mwebaze
🔗
|
Mon 9:35 a.m. - 10:00 a.m.
|
Dataset Shifts: 8 Years of Going from Practice to Theory to Policy and Future Directions
(
Invited talk
)
>
SlidesLive Video
|
Suchi Saria
🔗
|
Mon 10:00 a.m. - 10:25 a.m.
|
ML Model Debugging: A Data Perspective
(
Invited talk
)
>
SlidesLive Video
|
Aleksander Madry
🔗
|
Mon 10:30 a.m. - 11:00 a.m.
|
Discussion: Aleksander Mądry, Ernest Mwebaze, Suchi Saria
(
Panel
)
>
SlidesLive Video
|
Aleksander Madry · Ernest Mwebaze · Suchi Saria
🔗
|
Mon 11:00 a.m. - 11:25 a.m.
|
Increasing Robustness to Distribution Shifts by Improving Design
(
Invited talk
)
>
SlidesLive Video
|
Elizabeth Tipton
🔗
|
Mon 11:25 a.m. - 11:50 a.m.
|
Statistical Testing under Distribution Shifts
(
Invited talk
)
>
SlidesLive Video
|
Jonas Peters
🔗
|
Mon 11:50 a.m. - 12:10 p.m.
|
Discussion: Elizabeth Tipton, Jonas Peters
(
Panel
)
>
SlidesLive Video
|
Elizabeth Tipton · Jonas Peters
🔗
|
Mon 12:20 p.m. - 12:30 p.m.
|
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
(
Spotlight
)
>
link
SlidesLive Video
|
Neil Band · Tim G. J. Rudner · Qixuan Feng · Angelos Filos · Zachary Nado · Mike Dusenberry · Ghassen Jerfel · Dustin Tran · Yarin Gal
🔗
|
Mon 12:30 p.m. - 12:40 p.m.
|
A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs
(
Spotlight
)
>
link
SlidesLive Video
|
Mucong Ding · Kezhi Kong · Jiuhai Chen · John Kirchenbauer · Micah Goldblum · David P Wipf · Furong Huang · Tom Goldstein
🔗
|
Mon 12:40 p.m. - 12:50 p.m.
|
On Adaptivity and Confounding in Contextual Bandit Experiments
(
Spotlight
)
>
link
SlidesLive Video
|
Chao Qin · Daniel Russo
🔗
|
Mon 12:50 p.m. - 1:00 p.m.
|
Is Importance Weighting Incompatible with Interpolating Classifiers?
(
Spotlight
)
>
link
SlidesLive Video
|
Ke Alexander Wang · Niladri Chatterji · Saminul Haque · Tatsunori Hashimoto
🔗
|
Mon 1:00 p.m. - 3:00 p.m.
|
Poster session
(
Poster session
)
>
link
|
🔗
|
Mon 3:00 p.m. - 3:45 p.m.
|
Break / Lounge
link
|
🔗
|
Mon 3:50 p.m. - 4:15 p.m.
|
Importance Weighting for Transfer Learning
(
Invited talk
)
>
SlidesLive Video
|
Masashi Sugiyama
🔗
|
Mon 4:15 p.m. - 4:40 p.m.
|
Robustness through the Lens of Invariance
(
Invited talk
)
>
SlidesLive Video
|
Chelsea Finn
🔗
|
Mon 4:40 p.m. - 5:00 p.m.
|
Discussion: Chelsea Finn, Masashi Sugiyama
(
Panel
)
>
SlidesLive Video
|
Chelsea Finn · Masashi Sugiyama
🔗
|
Mon 5:00 p.m. - 6:00 p.m.
|
Panel: Future directions for tackling distribution shifts
(
Panel
)
>
SlidesLive Video
|
Tatsunori Hashimoto · Jamie Morgenstern · Judy Hoffman · Andrew Beck
🔗
|
-
|
On Adaptivity and Confounding in Contextual Bandit Experiments
(
Poster
)
>
link
|
Chao Qin · Daniel Russo
🔗
|
-
|
Exploring Covariate and Concept Shift for Out-of-Distribution Detection
(
Poster
)
>
link
SlidesLive Video
|
Junjiao Tian · Yen-Chang Hsu · Yilin Shen · Hongxia Jin · Zsolt Kira
🔗
|
-
|
Just Mix Once: Mixing Samples with Implicit Group Distribution
(
Poster
)
>
link
SlidesLive Video
|
Giorgio Giannone · Serhii Havrylov · Jordan Massiah · Emine Yilmaz · Yunlong Jiao
🔗
|
-
|
PCA Subspaces Are Not Always Optimal for Bayesian Learning
(
Poster
)
>
link
SlidesLive Video
|
Alexandre Bense · Amir Joudaki · Tim G. J. Rudner · Vincent Fortuin
🔗
|
-
|
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
(
Poster
)
>
link
|
Dan Hendrycks · Andy Zou · Mantas Mazeika · Leonard Tang · Dawn Song · Jacob Steinhardt
🔗
|
-
|
Quantifying and Alleviating Distribution Shifts in Foundation Models on Review Classification
(
Poster
)
>
link
SlidesLive Video
|
Sehaj Chawla · Nikhil Singh · Iddo Drori
🔗
|
-
|
Mixture of Basis for Interpretable Continual Learning with Distribution Shifts
(
Poster
)
>
link
SlidesLive Video
|
Mengda Xu · Sumitra Ganesh · Pranay Pasula
🔗
|
-
|
Ensembles and Cocktails: Robust Finetuning for Natural Language Generation
(
Poster
)
>
link
|
John Hewitt · Xiang Li · Sang Michael Xie · Benjamin Newman · Percy Liang
🔗
|
-
|
A benchmark with decomposed distribution shifts for 360 monocular depth estimation
(
Poster
)
>
link
SlidesLive Video
|
Georgios Albanis · Nikolaos Zioulis · Petros Drakoulis · Dimitrios Zarpalas · Petros Daras
🔗
|
-
|
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
(
Poster
)
>
link
|
Saurabh Garg · Sivaraman Balakrishnan · Zachary Lipton · Behnam Neyshabur · Hanie Sedghi
🔗
|
-
|
Improving Baselines in the Wild
(
Poster
)
>
link
|
Kazuki Irie · Imanol Schlag · Róbert Csordás · Jürgen Schmidhuber
🔗
|
-
|
Boosting worst-group accuracy without group annotations
(
Poster
)
>
link
SlidesLive Video
|
Vincent Bardenhagen · Alexandru Tifrea · Fanny Yang
🔗
|
-
|
Adversarial Training Blocks Generalization in Neural Policies
(
Poster
)
>
link
SlidesLive Video
|
Ezgi Korkmaz
🔗
|
-
|
Revisiting Visual Product for Compositional Zero-Shot Learning
(
Poster
)
>
link
SlidesLive Video
|
Shyamgopal Karthik · Massimiliano Mancini · Zeynep Akata
🔗
|
-
|
Nonparametric Approach to Uncertainty Quantification for Deterministic Neural Networks
(
Poster
)
>
link
|
Nikita Kotelevskii · Alexander Fishkov · Kirill Fedyanin · Aleksandr Petiushko · Maxim Panov
🔗
|
-
|
Towards Robust and Adaptable Motion Forecasting: A Causal Representation Perspective
(
Poster
)
>
link
|
Yuejiang Liu · Alexandre Alahi
🔗
|
-
|
A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs
(
Poster
)
>
link
SlidesLive Video
|
Mucong Ding · Kezhi Kong · Jiuhai Chen · John Kirchenbauer · Micah Goldblum · David P Wipf · Furong Huang · Tom Goldstein
🔗
|
-
|
Shift and Scale is Detrimental To Few-Shot Transfer
(
Poster
)
>
link
|
Moslem Yazdanpanah · Christian Desrosiers · Mohammad Havaei · Eugene Belilovsky · Samira Ebrahimi Kahou
🔗
|
-
|
Calibrated Ensembles: A Simple Way to Mitigate ID-OOD Accuracy Tradeoffs
(
Poster
)
>
link
SlidesLive Video
|
Ananya Kumar · Aditi Raghunathan · Tengyu Ma · Percy Liang
🔗
|
-
|
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
(
Poster
)
>
link
|
Michael Zhang · Nimit Sohoni · Hongyang Zhang · Chelsea Finn · Christopher Ré
🔗
|
-
|
Domain-agnostic Test-time Adaptation by Prototypical Training with Auxiliary Data
(
Poster
)
>
link
SlidesLive Video
|
Qilong Wu · Xiangyu Yue · Alberto Sangiovanni-Vincentelli
🔗
|
-
|
Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
(
Poster
)
>
link
SlidesLive Video
|
Aadarsh Sahoo · Rameswar Panda · Rogerio Feris · Kate Saenko · Abir Das
🔗
|
-
|
Spectrally Adaptive Common Spatial Patterns
(
Poster
)
>
link
|
Mahta Mousavi · Eric Lybrand · Shuangquan Feng · Shuai Tang · Rayan Saab · Virginia de Sa
🔗
|
-
|
How Does Contrastive Pre-training Connect Disparate Domains?
(
Poster
)
>
link
SlidesLive Video
|
Kendrick Shen · Robert Jones · Ananya Kumar · Sang Michael Xie · Percy Liang
🔗
|
-
|
Handling Distribution Shift in Tire Design
(
Poster
)
>
link
SlidesLive Video
|
Antoine De mathelin · François Deheeger · Mathilde MOUGEOT · Nicolas Vayatis
🔗
|
-
|
Learning Invariant Representations with Missing Data
(
Poster
)
>
link
|
Mark Goldstein · Adriel Saporta · Aahlad Puli · Rajesh Ranganath · Andrew Miller
🔗
|
-
|
Multi-Domain Ensembles for Domain Generalization
(
Poster
)
>
link
|
Kowshik Thopalli · Sameeksha Katoch · Jayaraman Thiagarajan · Pavan Turaga · Andreas Spanias
🔗
|
-
|
Benchmarking Robustness to Natural Distribution Shifts for Facial Analysis
(
Poster
)
>
link
SlidesLive Video
|
Jessica Deuschel · Andreas Foltyn
🔗
|
-
|
Distribution Shift in Airline Customer Behavior during COVID-19
(
Poster
)
>
link
SlidesLive Video
|
Abhinav Garg · naman shukla · Lavanya Marla · Sriram Somanchi
🔗
|
-
|
Extending the WILDS Benchmark for Unsupervised Adaptation
(
Poster
)
>
link
|
18 presenters
Shiori Sagawa · Pang Wei Koh · Tony Lee · Irena Gao · Sang Michael Xie · Kendrick Shen · Ananya Kumar · Weihua Hu · Michihiro Yasunaga · Henrik Marklund · Sara Beery · Ian Stavness · Jure Leskovec · Kate Saenko · Tatsunori Hashimoto · Sergey Levine · Chelsea Finn · Percy Liang
🔗
|
-
|
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts
(
Poster
)
>
link
|
Nader Asadi · Sudhir Mudur · Eugene Belilovsky
🔗
|
-
|
Avoiding Spurious Correlations: Bridging Theory and Practice
(
Poster
)
>
link
|
Thao Nguyen · Hanie Sedghi · Behnam Neyshabur
🔗
|
-
|
Model Zoo: A Growing Brain That Learns Continually
(
Poster
)
>
link
SlidesLive Video
|
Rahul Ramesh · Pratik Chaudhari
🔗
|
-
|
The impact of domain shift on the calibration of fine-tuned models
(
Poster
)
>
link
|
Jay Mohta · Colin Raffel
🔗
|
-
|
Probing Representation Forgetting in Continual Learning
(
Poster
)
>
link
|
MohammadReza Davari · Eugene Belilovsky
🔗
|
-
|
Kernel Landmarks: An Empirical Statistical Approach to Detect Covariate Shift
(
Poster
)
>
link
SlidesLive Video
|
Yuksel Karahan · Bilal Riaz · Austin J Brockmeier
🔗
|
-
|
A Unified DRO View of Multi-class Loss Functions with top-N Consistency
(
Poster
)
>
link
SlidesLive Video
|
Dixian Zhu · Tianbao Yang
🔗
|
-
|
Re-labeling Domains Improves Multi-Domain Generalization
(
Poster
)
>
link
SlidesLive Video
|
Kowshik Thopalli · Pavan Turaga · Jayaraman Thiagarajan
🔗
|
-
|
Using Distributionally Robust Optimization to improve robustness in cancer pathology
(
Poster
)
>
link
SlidesLive Video
|
Surya Narayanan Hari
🔗
|
-
|
Thinking Beyond Distributions in Testing Machine Learned Models
(
Poster
)
>
link
|
Negar Rostamzadeh · Ben Hutchinson · Vinodkumar Prabhakaran
🔗
|
-
|
Exploiting Causal Chains for Domain Generalization
(
Poster
)
>
link
SlidesLive Video
|
Olawale Salaudeen · Sanmi Koyejo
🔗
|
-
|
KitchenShift: Evaluating Zero-Shot Generalization of Imitation-Based Policy Learning Under Domain Shifts
(
Poster
)
>
link
SlidesLive Video
|
Eliot Xing · Abhinav Gupta · Samantha Powers · Victoria Dean
🔗
|
-
|
Distributionally Robust Group Backwards Compatibility
(
Poster
)
>
link
SlidesLive Video
|
Martin Bertran · Natalia Martinez · Guillermo Sapiro
🔗
|
-
|
Understanding and Improving Robustness of VisionTransformers through patch-based NegativeAugmentation
(
Poster
)
>
link
|
Yao Qin · Chiyuan Zhang · Ting Chen · Balaji Lakshminarayanan · Alex Beutel · Xuezhi Wang
🔗
|
-
|
Unsupervised Attribute Alignment for Characterizing Distribution Shift
(
Poster
)
>
link
|
Matthew Olson · Rushil Anirudh · Jayaraman Thiagarajan · Timo Bremer · Weng-Keen Wong · Shusen Liu
🔗
|
-
|
Identifying the Instances Associated with Distribution Shifts using the Max-Sliced Bures Divergence
(
Poster
)
>
link
SlidesLive Video
|
Austin J Brockmeier · Claudio Claros-Olivares · Luis G Sanchez Giraldo
🔗
|
-
|
BEDS-Bench: Behavior of EHR-models under Distributional Shift - A Benchmark
(
Poster
)
>
link
|
Anand Avati · Martin Seneviratne · Yuan Xue · Zhen Xu · Balaji Lakshminarayanan · Andrew Dai
🔗
|
-
|
Test Time Robustification of Deep Models via Adaptation and Augmentation
(
Poster
)
>
link
|
Marvin Zhang · Sergey Levine · Chelsea Finn
🔗
|
-
|
Catastrophic Failures of Neural Active Learning on Heteroskedastic Distributions
(
Poster
)
>
link
SlidesLive Video
|
Savya Khosla · Alex Lamb · Jordan Ash · Cyril Zhang · Kenji Kawaguchi
🔗
|
-
|
Jointly Learning from Decentralized (Federated) and Centralized Data to Mitigate Distribution Shift
(
Poster
)
>
link
|
Sean Augenstein · Andrew S Hard · Rajiv Mathews
🔗
|
-
|
Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
(
Poster
)
>
link
SlidesLive Video
|
Kehang Han · Balaji Lakshminarayanan · Jeremiah Liu
🔗
|
-
|
Distribution Preserving Bayesian Coresets using Set Constraints
(
Poster
)
>
link
SlidesLive Video
|
Shovik Guha · Rajiv Khanna · Sanmi Koyejo
🔗
|
-
|
Causal-based Time Series Domain Generalization for Vehicle Intention Prediction
(
Poster
)
>
link
SlidesLive Video
|
Yeping Hu · Xiaogang Jia · Masayoshi TOMIZUKA · Wei Zhan
🔗
|
-
|
Robust fine-tuning of zero-shot models
(
Poster
)
>
link
|
Mitchell Wortsman · Gabriel Ilharco · Jong Wook Kim · Mike Li · Hanna Hajishirzi · Ali Farhadi · Hongseok Namkoong · Ludwig Schmidt
🔗
|
-
|
Are Vision Transformers Always More Robust Than Convolutional Neural Networks?
(
Poster
)
>
link
SlidesLive Video
|
Francesco Pinto · Philip Torr · Puneet Dokania
🔗
|
-
|
Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance
(
Poster
)
>
link
SlidesLive Video
|
Shibal Ibrahim · Natalia Ponomareva · Rahul Mazumder
🔗
|
-
|
Mix-MaxEnt: Improving Accuracy and Uncertainty Estimates of Deterministic Neural Networks
(
Poster
)
>
link
SlidesLive Video
|
Francesco Pinto · Harry Yang · Ser Nam Lim · Philip Torr · Puneet Dokania
🔗
|
-
|
On The Reliability Of Machine Learning Applications In Manufacturing Environments
(
Poster
)
>
link
|
Nicolas Jourdan
🔗
|
-
|
Igeood: An Information Geometry Approach to Out-of-Distribution Detection
(
Poster
)
>
link
SlidesLive Video
|
Eduardo Dadalto · Florence Alberge · Pierre Duhamel · Pablo Piantanida
🔗
|
-
|
Towards Data-Free Domain Generalization
(
Poster
)
>
link
SlidesLive Video
|
Ahmed Frikha · Haokun Chen · Denis Krompaß · Thomas Runkler · Volker Tresp
🔗
|
-
|
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
(
Poster
)
>
link
SlidesLive Video
|
Neil Band · Tim G. J. Rudner · Qixuan Feng · Angelos Filos · Zachary Nado · Mike Dusenberry · Ghassen Jerfel · Dustin Tran · Yarin Gal
🔗
|
-
|
Continual Density Ratio Estimation
(
Poster
)
>
link
SlidesLive Video
|
Yu Chen · Song Liu · Tom Diethe · Peter Flach
🔗
|
-
|
Gradient-matching coresets for continual learning
(
Poster
)
>
link
SlidesLive Video
|
Lukas Balles · Giovanni Zappella · Cedric Archambeau
🔗
|
-
|
Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks
(
Poster
)
>
link
SlidesLive Video
|
Alexander Fuchs · Christian Knoll · Franz Pernkopf
🔗
|
-
|
Augmented Self-Labeling for Source-Free Unsupervised Domain Adaptation
(
Poster
)
>
link
SlidesLive Video
|
Hao Yan · · Chunsheng Yang
🔗
|
-
|
An Empirical Study of Pre-trained Models on Out-of-distribution Generalization
(
Poster
)
>
link
SlidesLive Video
|
Yaodong Yu · Heinrich Jiang · Dara Bahri · Hossein Mobahi · Seungyeon Kim · Ankit Rawat · Andreas Veit · Yi Ma
🔗
|
-
|
Randomly projecting out distribution shifts for improved robustness
(
Poster
)
>
link
SlidesLive Video
|
Isabela Albuquerque · Joao Monteiro · Tiago H Falk
🔗
|
-
|
Semi-Supervised Domain Generalization with Stochastic StyleMatch
(
Poster
)
>
link
|
Kaiyang Zhou · Chen Change Loy · Ziwei Liu
🔗
|
-
|
Understanding Post-hoc Adaptation for Improving Subgroup Robustness
(
Poster
)
>
link
SlidesLive Video
|
David Madras · Richard Zemel
🔗
|
-
|
Optimal Representations for Covariate Shifts
(
Poster
)
>
link
SlidesLive Video
|
Yann Dubois · Yangjun Ruan · Chris Maddison
🔗
|
-
|
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration
(
Poster
)
>
link
|
Ryan Soklaski · Michael Yee · Theodoros Tsiligkaridis
🔗
|
-
|
Test time Adaptation through Perturbation Robustness
(
Poster
)
>
link
SlidesLive Video
|
Prabhu Teja Sivaprasad · François Fleuret
🔗
|
-
|
Diurnal or Nocturnal? Federated Learning from Periodically Shifting Distributions
(
Poster
)
>
link
|
Chen Zhu · Zheng Xu · Mingqing Chen · Jakub Konečný · Andrew S Hard · Tom Goldstein
🔗
|
-
|
Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift
(
Poster
)
>
link
SlidesLive Video
|
Liwen Ouyang · Aaron Key
🔗
|
-
|
A fine-grained analysis of robustness to distribution shifts
(
Poster
)
>
link
SlidesLive Video
|
Olivia Wiles · Sven Gowal · Florian Stimberg · Sylvestre-Alvise Rebuffi · Ira Ktena · Krishnamurthy Dvijotham · Taylan Cemgil
🔗
|
-
|
Is Importance Weighting Incompatible with Interpolating Classifiers?
(
Poster
)
>
link
SlidesLive Video
|
Ke Alexander Wang · Niladri Chatterji · Saminul Haque · Tatsunori Hashimoto
🔗
|
-
|
Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency
(
Poster
)
>
link
SlidesLive Video
|
Samarth Mishra · Kate Saenko · Venkatesh Saligrama
🔗
|
-
|
Self-supervised Learning is More Robust to Dataset Imbalance
(
Poster
)
>
link
|
Hong Liu · Jeff Z. HaoChen · Adrien Gaidon · Tengyu Ma
🔗
|
-
|
Effect of Model Size on Worst-group Generalization
(
Poster
)
>
link
SlidesLive Video
|
Alan Pham · Eunice Chan · Vikranth Srivatsa · Dhruba Ghosh · Yaoqing Yang · Yaodong Yu · Ruiqi Zhong · Joseph Gonzalez · Jacob Steinhardt
🔗
|
-
|
Smooth Transfer Learning for Source-to-Target Generalization
(
Poster
)
>
link
SlidesLive Video
|
Keita Takayama · Teppei Suzuki · Ikuro Sato · Rei Kawakami · Koichi Shinoda
🔗
|
-
|
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
(
Poster
)
>
link
SlidesLive Video
|
Paul Gavrikov · Janis Keuper
🔗
|
-
|
DANNTe: a case study of a turbo-machinery sensor virtualization under domain shift
(
Poster
)
>
link
SlidesLive Video
|
Valentina Gori · Luca Strazzera
🔗
|
-
|
Internalized Biases in Fréchet Inception Distance
(
Poster
)
>
link
SlidesLive Video
|
Steffen Jung · Margret Keuper
🔗
|
-
|
Investigating Shifts in GAN Output-Distributions
(
Poster
)
>
link
SlidesLive Video
|
Ricard Durall · Janis Keuper
🔗
|
-
|
Con$^{2}$DA: Simplifying Semi-supervised Domain Adaptation by Learning Consistent and Contrastive Feature Representations
(
Poster
)
>
link
SlidesLive Video
|
Manuel Perez · Guillermo Cabrera-Vives · Pavlos Protopapas
🔗
|