Timezone: »
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model’s sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anti-causal elements. We motivate this approach, Risk Extrapolation (REx), as a form of robust optimization over a perturbation set of extrapolated domains (MM-REx), and propose a penalty on the variance of training risks (V-REx) as a simpler variant. We prove that variants of REx can recover the causal mechanisms of the targets, while also providing robustness to changes in the input distribution (``covariate shift''). By appropriately trading-off robustness to causally induced distributional shifts and covariate shift, REx is able to outperform alternative methods such as Invariant Risk Minimization in situations where these types of shift co-occur.
Author Information
David Krueger (MILA (University of Montreal))
Ethan Caballero (Mila)
Joern-Henrik Jacobsen (Apple Inc.)
Amy Zhang (FAIR / UC Berkeley)
Jonathan Binas (Mila, Montreal)
Dinghuai Zhang (Mila)
Remi Le Priol (Mila, Université de Montréal)
Aaron Courville (Université de Montréal)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Out-of-Distribution Generalization via Risk Extrapolation (REx) »
Wed. Jul 21st 04:00 -- 06:00 AM Room
More from the Same Authors
-
2020 : Learning Invariant Representations for Reinforcement Learning without Reconstruction »
Amy Zhang -
2020 : Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP »
Amy Zhang -
2021 : Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA »
Sébastien Lachapelle · Pau Rodriguez · Remi Le Priol · Alexandre Lacoste -
2022 : P24: Unifying Generative Models with GFlowNets »
Dinghuai Zhang · Ricky T. Q. Chen -
2022 : Defining and Characterizing Reward Gaming »
Joar Skalse · Nikolaus Howe · Dmitrii Krasheninnikov · David Krueger -
2023 : Towards Out-of-Distribution Adversarial Robustness »
Adam Ibrahim · Charles Guille-Escuret · Ioannis Mitliagkas · Irina Rish · David Krueger · Pouya Bashivan -
2023 : Suboptimal Data Can Bottleneck Scaling »
Jacob Buckman · Kshitij Gupta · Ethan Caballero · Rishabh Agarwal · Marc Bellemare -
2023 : Conditional Bisimulation for Generalization in Reinforcement Learning »
Anuj Mahajan · Amy Zhang -
2023 Workshop: Structured Probabilistic Inference and Generative Modeling »
Dinghuai Zhang · Yuanqi Du · Chenlin Meng · Shawn Tan · Yingzhen Li · Max Welling · Yoshua Bengio -
2023 : Opening Remark »
Dinghuai Zhang · Yuanqi Du · Chenlin Meng · Shawn Tan · Yingzhen Li · Max Welling · Yoshua Bengio -
2023 Poster: GFlowOut: Dropout with Generative Flow Networks »
Dianbo Liu · Moksh Jain · Bonaventure F. P. Dossou · Qianli Shen · Salem Lahlou · Anirudh Goyal · Nikolay Malkin · Chris Emezue · Dinghuai Zhang · Nadhir Hassen · Xu Ji · Kenji Kawaguchi · Yoshua Bengio -
2023 Poster: Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning »
Tongzhou Wang · Antonio Torralba · Phillip Isola · Amy Zhang -
2023 Poster: Mechanistic Mode Connectivity »
Ekdeep Singh Lubana · Eric Bigelow · Robert Dick · David Krueger · Hidenori Tanaka -
2023 Poster: Better Training of GFlowNets with Local Credit and Incomplete Trajectories »
Ling Pan · Nikolay Malkin · Dinghuai Zhang · Yoshua Bengio -
2023 Poster: LIV: Language-Image Representations and Rewards for Robotic Control »
Yecheng Jason Ma · Vikash Kumar · Amy Zhang · Osbert Bastani · Dinesh Jayaraman -
2023 Poster: A theory of continuous generative flow networks »
Salem Lahlou · Tristan Deleu · Pablo Lemos · Dinghuai Zhang · Alexandra Volokhova · Alex Hernandez-Garcia · Lena Nehale Ezzine · Yoshua Bengio · Nikolay Malkin -
2022 : Invited talks 3, Q/A, Amy, Rich and Liting »
Liting Sun · Amy Zhang · Richard Zemel -
2022 : Invited talks 3, Amy Zhang, Rich Zemel and Liting Sun »
Amy Zhang · Richard Zemel · Liting Sun -
2022 Poster: Online Decision Transformer »
Qinqing Zheng · Amy Zhang · Aditya Grover -
2022 Poster: Building Robust Ensembles via Margin Boosting »
Dinghuai Zhang · Hongyang Zhang · Aaron Courville · Yoshua Bengio · Pradeep Ravikumar · Arun Sai Suggala -
2022 Poster: Robust Policy Learning over Multiple Uncertainty Sets »
Annie Xie · Shagun Sodhani · Chelsea Finn · Joelle Pineau · Amy Zhang -
2022 Poster: Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning »
Philippe Hansen-Estruch · Amy Zhang · Ashvin Nair · Patrick Yin · Sergey Levine -
2022 Spotlight: Robust Policy Learning over Multiple Uncertainty Sets »
Annie Xie · Shagun Sodhani · Chelsea Finn · Joelle Pineau · Amy Zhang -
2022 Spotlight: Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning »
Philippe Hansen-Estruch · Amy Zhang · Ashvin Nair · Patrick Yin · Sergey Levine -
2022 Oral: Online Decision Transformer »
Qinqing Zheng · Amy Zhang · Aditya Grover -
2022 Spotlight: Building Robust Ensembles via Margin Boosting »
Dinghuai Zhang · Hongyang Zhang · Aaron Courville · Yoshua Bengio · Pradeep Ravikumar · Arun Sai Suggala -
2022 Poster: Biological Sequence Design with GFlowNets »
Moksh Jain · Emmanuel Bengio · Alex Hernandez-Garcia · Jarrid Rector-Brooks · Bonaventure Dossou · Chanakya Ekbote · Jie Fu · Tianyu Zhang · Michael Kilgour · Dinghuai Zhang · Lena Simine · Payel Das · Yoshua Bengio -
2022 Poster: Denoised MDPs: Learning World Models Better Than the World Itself »
Tongzhou Wang · Simon Du · Antonio Torralba · Phillip Isola · Amy Zhang · Yuandong Tian -
2022 Spotlight: Denoised MDPs: Learning World Models Better Than the World Itself »
Tongzhou Wang · Simon Du · Antonio Torralba · Phillip Isola · Amy Zhang · Yuandong Tian -
2022 Spotlight: Biological Sequence Design with GFlowNets »
Moksh Jain · Emmanuel Bengio · Alex Hernandez-Garcia · Jarrid Rector-Brooks · Bonaventure Dossou · Chanakya Ekbote · Jie Fu · Tianyu Zhang · Michael Kilgour · Dinghuai Zhang · Lena Simine · Payel Das · Yoshua Bengio -
2022 Poster: Generative Flow Networks for Discrete Probabilistic Modeling »
Dinghuai Zhang · Nikolay Malkin · Zhen Liu · Alexandra Volokhova · Aaron Courville · Yoshua Bengio -
2022 Poster: The Primacy Bias in Deep Reinforcement Learning »
Evgenii Nikishin · Max Schwarzer · Pierluca D'Oro · Pierre-Luc Bacon · Aaron Courville -
2022 Spotlight: Generative Flow Networks for Discrete Probabilistic Modeling »
Dinghuai Zhang · Nikolay Malkin · Zhen Liu · Alexandra Volokhova · Aaron Courville · Yoshua Bengio -
2022 Spotlight: The Primacy Bias in Deep Reinforcement Learning »
Evgenii Nikishin · Max Schwarzer · Pierluca D'Oro · Pierre-Luc Bacon · Aaron Courville -
2021 Poster: Environment Inference for Invariant Learning »
Elliot Creager · Joern-Henrik Jacobsen · Richard Zemel -
2021 Spotlight: Environment Inference for Invariant Learning »
Elliot Creager · Joern-Henrik Jacobsen · Richard Zemel -
2021 Poster: Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization? »
Dinghuai Zhang · Kartik Ahuja · Yilun Xu · Yisen Wang · Aaron Courville -
2021 Oral: Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization? »
Dinghuai Zhang · Kartik Ahuja · Yilun Xu · Yisen Wang · Aaron Courville -
2021 Poster: Continuous Coordination As a Realistic Scenario for Lifelong Learning »
Hadi Nekoei · Akilesh Badrinaaraayanan · Aaron Courville · Sarath Chandar -
2021 Spotlight: Continuous Coordination As a Realistic Scenario for Lifelong Learning »
Hadi Nekoei · Akilesh Badrinaaraayanan · Aaron Courville · Sarath Chandar -
2021 Poster: Multi-Task Reinforcement Learning with Context-based Representations »
Shagun Sodhani · Amy Zhang · Joelle Pineau -
2021 Spotlight: Multi-Task Reinforcement Learning with Context-based Representations »
Shagun Sodhani · Amy Zhang · Joelle Pineau -
2020 : Paper spotlight: Learning Invariant Representations for Reinforcement Learning without Reconstruction »
Amy Zhang -
2020 Poster: AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation »
Jae Hyun Lim · Aaron Courville · Christopher Pal · Chin-Wei Huang -
2020 Poster: Countering Language Drift with Seeded Iterated Learning »
Yuchen Lu · Soumye Singhal · Florian Strub · Aaron Courville · Olivier Pietquin -
2020 Poster: How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization »
Chris Finlay · Joern-Henrik Jacobsen · Levon Nurbekyan · Adam Oberman -
2020 Poster: Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations »
Florian Tramer · Jens Behrmann · Nicholas Carlini · Nicolas Papernot · Joern-Henrik Jacobsen -
2020 Poster: Informative Dropout for Robust Representation Learning: A Shape-bias Perspective »
Baifeng Shi · Dinghuai Zhang · Qi Dai · Zhanxing Zhu · Yadong Mu · Jingdong Wang -
2020 Poster: Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling »
Will Grathwohl · Kuan-Chieh Wang · Joern-Henrik Jacobsen · David Duvenaud · Richard Zemel -
2020 Affinity Workshop: Women in Machine Learning Un-Workshop »
Tatjana Chavdarova · Caroline Weis · Amy Zhang · Fariba Yousefi · Mandana Samiei · Larissa Schiavo -
2019 : Poster Session #1 »
Adrien Ali Taiga · Aniket Anand Deshmukh · Tabish Rashid · Jonathan Binas · Nikolaus Yasui · Vitchyr Pong · Takahisa Imagawa · Jesse Clifton · Siddharth Mysore · Shi-Chun Tsai · Caleb Chuck · Giulia Vezzani · Hannes Bengt Eriksson -
2019 Workshop: Invertible Neural Networks and Normalizing Flows »
Chin-Wei Huang · David Krueger · Rianne Van den Berg · George Papamakarios · Aidan Gomez · Chris Cremer · Aaron Courville · Ricky T. Q. Chen · Danilo J. Rezende -
2019 : Poster discussion »
Roman Novak · Maxime Gabella · Frederic Dreyer · Siavash Golkar · Anh Tong · Irina Higgins · Mirco Milletari · Joe Antognini · Sebastian Goldt · Adín Ramírez Rivera · Roberto Bondesan · Ryo Karakida · Remi Tachet des Combes · Michael Mahoney · Nicholas Walker · Stanislav Fort · Samuel Smith · Rohan Ghosh · Aristide Baratin · Diego Granziol · Stephen Roberts · Dmitry Vetrov · Andrew Wilson · César Laurent · Valentin Thomas · Simon Lacoste-Julien · Dar Gilboa · Daniel Soudry · Anupam Gupta · Anirudh Goyal · Yoshua Bengio · Erich Elsen · Soham De · Stanislaw Jastrzebski · Charles H Martin · Samira Shabanian · Aaron Courville · Shorato Akaho · Lenka Zdeborova · Ethan Dyer · Maurice Weiler · Pim de Haan · Taco Cohen · Max Welling · Ping Luo · zhanglin peng · Nasim Rahaman · Loic Matthey · Danilo J. Rezende · Jaesik Choi · Kyle Cranmer · Lechao Xiao · Jaehoon Lee · Yasaman Bahri · Jeffrey Pennington · Greg Yang · Jiri Hron · Jascha Sohl-Dickstein · Guy Gur-Ari -
2019 : "Ideas" mini-spotlights »
Kevin McCloskey · Nikola Milojevic-Dupont · Jonathan Binas · Christian Schroeder · Sasha Luccioni -
2019 : Invertible Residual Networks and a Novel Perspective on Adversarial Examples »
Joern-Henrik Jacobsen -
2019 : Networking Lunch (provided) + Poster Session »
Abraham Stanway · Alex Robson · Aneesh Rangnekar · Ashesh Chattopadhyay · Ashley Pilipiszyn · Benjamin LeRoy · Bolong Cheng · Ce Zhang · Chaopeng Shen · Christian Schroeder · Christian Clough · Clement DUHART · Clement Fung · Cozmin Ududec · Dali Wang · David Dao · di wu · Dimitrios Giannakis · Dino Sejdinovic · Doina Precup · Duncan Watson-Parris · Gege Wen · George Chen · Gopal Erinjippurath · Haifeng Li · Han Zou · Herke van Hoof · Hillary A Scannell · Hiroshi Mamitsuka · Hongbao Zhang · Jaegul Choo · James Wang · James Requeima · Jessica Hwang · Jinfan Xu · Johan Mathe · Jonathan Binas · Joonseok Lee · Kalai Ramea · Kate Duffy · Kevin McCloskey · Kris Sankaran · Lester Mackey · Letif Mones · Loubna Benabbou · Lynn Kaack · Matthew Hoffman · Mayur Mudigonda · Mehrdad Mahdavi · Michael McCourt · Mingchao Jiang · Mohammad Mahdi Kamani · Neel Guha · Niccolo Dalmasso · Nick Pawlowski · Nikola Milojevic-Dupont · Paulo Orenstein · Pedram Hassanzadeh · Pekka Marttinen · Ramesh Nair · Sadegh Farhang · Samuel Kaski · Sandeep Manjanna · Sasha Luccioni · Shuby Deshpande · Soo Kim · Soukayna Mouatadid · Sunghyun Park · Tao Lin · Telmo Felgueira · Thomas Hornigold · Tianle Yuan · Tom Beucler · Tracy Cui · Volodymyr Kuleshov · Wei Yu · yang song · Ydo Wexler · Yoshua Bengio · Zhecheng Wang · Zhuangfang Yi · Zouheir Malki -
2019 Poster: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations »
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer -
2019 Poster: Flexibly Fair Representation Learning by Disentanglement »
Elliot Creager · David Madras · Joern-Henrik Jacobsen · Marissa Weis · Kevin Swersky · Toniann Pitassi · Richard Zemel -
2019 Poster: Hierarchical Importance Weighted Autoencoders »
Chin-Wei Huang · Kris Sankaran · Eeshan Dhekane · Alexandre Lacoste · Aaron Courville -
2019 Oral: Hierarchical Importance Weighted Autoencoders »
Chin-Wei Huang · Kris Sankaran · Eeshan Dhekane · Alexandre Lacoste · Aaron Courville -
2019 Oral: Flexibly Fair Representation Learning by Disentanglement »
Elliot Creager · David Madras · Joern-Henrik Jacobsen · Marissa Weis · Kevin Swersky · Toniann Pitassi · Richard Zemel -
2019 Oral: State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations »
Alex Lamb · Jonathan Binas · Anirudh Goyal · Sandeep Subramanian · Ioannis Mitliagkas · Yoshua Bengio · Michael Mozer -
2019 Poster: Invertible Residual Networks »
Jens Behrmann · Will Grathwohl · Ricky T. Q. Chen · David Duvenaud · Joern-Henrik Jacobsen -
2019 Oral: Invertible Residual Networks »
Jens Behrmann · Will Grathwohl · Ricky T. Q. Chen · David Duvenaud · Joern-Henrik Jacobsen -
2018 Poster: Composable Planning with Attributes »
Amy Zhang · Sainbayar Sukhbaatar · Adam Lerer · Arthur Szlam · Facebook Rob Fergus -
2018 Oral: Composable Planning with Attributes »
Amy Zhang · Sainbayar Sukhbaatar · Adam Lerer · Arthur Szlam · Facebook Rob Fergus