Conditional variance penalties and domain shift robustness

Keywords

Robustness (evolution), Artificial intelligence, Latent variable, Computer science, Invariant (physics)

References

• Multi-Source Domain Adaptation: A Causal ViewKun Zhang, Mingming Gong, Bernhard Schoelkopf — 2015
• Robust Solutions of Optimization Problems Affected by Uncertain ProbabilitiesAharon Ben‐Tal, Dick den Hertog, Anja De Waegenaere — 2013
• Topics in Optimal TransportationCédric Villani — 2003
• A Survey on Multi-view LearningChang Xu, Dacheng Tao, Chao Xu — 2013
• Intriguing properties of neural networksChristian Szegedy, Wojciech Zaremba, Ilya Sutskever — 2013
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
• Big Data's Disparate ImpactSolon Barocas, Andrew D. Selbst — 2016
• Deep Learning Face Attributes in the WildZiwei Liu, Ping Luo, Xiaogang Wang — 2014
• Causal inference by using invariant prediction: identification and confidence intervalsJonas Peters, Peter Bühlmann, Nicolai Meinshausen — 2015
• Convexity, Classification, and Risk BoundsPeter L. Bartlett, Michael I. Jordan, Jon McAuliffe — 2006
• Bayesian inference for variance components using only error contrastsDavid A. Harville — 1974
• Unbiased look at dataset biasAntonio Torralba, Alexei A. Efros — 2011
• The probability approach in econometricsTrygve Haavelmo — 1944
• Going deeper with convolutionsChristian Szegedy, Wei Liu, Yangqing Jia — 2014
• Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled ExamplesMikhail Belkin, Partha Niyogi, Vikas Sindhwani — 2006
• Gradient-based learning applied to document recognitionYann LeCun, Léon Bottou, Yoshua Bengio — 1998
• Robust Regression and LassoHuan Xu, Constantine Caramanis, Shie Mannor — 2008
• Conditional Generative Adversarial NetsMehdi Mirza, Simon Osindero — 2014
• Learning Invariant Representations with Local TransformationsKihyuk Sohn, Honglak Lee — 2012
• Viewpoint Invariant Face Recognition using Independent Component Analysis and Attractor NetworksMarian Stewart Bartlett, Terrence J. Sejnowski — 1996

Cited by

• Anchor regression: Heterogeneous data meet causalityDominik Rothenhaüsler, Nicolai Meinshausen, Peter Bühlmann — 2018
• CAUSALITY FROM A DISTRIBUTIONAL ROBUSTNESS POINT OF VIEWNicolai Meinshausen — 2018
• Logit Pairing Methods Can Fool Gradient-Based AttacksMarius Mosbach, Maksym Andriushchenko, Thomas Alexander Trost — 2018
• Invariance, Causality and RobustnessPeter Bühlmann — 2018
• A Universal Hierarchy of Shift-Stable Distributions and the Tradeoff Between Stability and PerformanceAdarsh Subbaswamy, Bryant Chen, Suchi Saria — 2019
• Should I Include this Edge in my Prediction? Analyzing the Stability-Performance TradeoffAdarsh Subbaswamy, Bryant Chen, Suchi Saria — 2019
• Semi-supervised learning, causality, and the conditional cluster assumptionJulius von Kügelgen, Alexander Mey, Marco Loog — 2019
• Regularization, Adaptation and Generalization of Neural NetworksRiccardo Volpi — 2019
• Invariant Risk MinimizationMartín Arjovsky, Léon Bottou, Ishaan Gulrajani — 2019
• Generalizing to Unseen Domains via Adversarial Data AugmentationRiccardo Volpi, Hongseok Namkoong, Ozan Şener — 2018
• Addressing Model Vulnerability to Distributional Shifts Over Image Transformation SetsRiccardo Volpi, Vittorio Murino — 2019
• Latent group structure and regularized regressionKonstantinos Perrakis, Lartigue, Thomas, Frank Dondelinger — 2019
• Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustnessFanny Yang, Zuowen Wang, Christina Heinze‐Deml — 2019
• A Causal View on Robustness of Neural NetworksCheng Zhang, Kun Zhang, Yingzhen Li — 2020
• Robust learning with the Hilbert-Schmidt independence criterionDaniel Greenfeld, Uri Shalit — 2019
• The Hierarchy of Stable Distributions and Operators to Trade Off Stability and PerformanceAdarsh Subbaswamy, Bryant Chen, Suchi Saria — 2019
• Stabilizing variable selection and regressionNiklas Pfister, Evan G. Williams, Jonas Peters — 2019
• Causality for Machine LearningBernhard Schölkopf — 2019
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case GeneralizationShiori Sagawa, Pang Wei Koh, Tatsunori Hashimoto — 2019
• Chances and challenges of machine learning based disease classification in genetic association studies illustrated on age-related macular degenerationFelix Günther, Caroline Brandl, Thomas W. Winkler — 2019

Related papers

• Unbiased look at dataset biasAntonio Torralba, Alexei A. Efros — 2011
• Grouping-By-ID: Guarding Against Adversarial Domain ShiftsChristina Heinze‐Deml, Nicolai Meinshausen — 2017
• Invariant Risk MinimizationMartín Arjovsky, Léon Bottou, Ishaan Gulrajani — 2019
• Elements of Causal Inference: Foundations and Learning AlgorithmsJonas Peters, Dominik Janzing, Bernhard Schölkopf — 2017
• CAUSALITY FROM A DISTRIBUTIONAL ROBUSTNESS POINT OF VIEWNicolai Meinshausen — 2018
• On causal and anticausal learningDominik Janzing, Jonas Peters, Eleni Sgouritsa — 2012