distribution shift

Near-Optimal Linear Regression under Distribution Shift ICML 2021 ODIST: Open World Classification via Distributionally Shifted Instances EMNLP 2021 Online Adaptation to Label Distribution Shift NeurIPS 2021 Online Continual Learning With Natural Distribution Shifts: An Empirical Study With Visual Data ICCV 2021 On Robust Mean Estimation under Coordinate-level Corruption ICML 2021 On Robustness and Transferability of Convolutional Neural Networks CVPR 2021 On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift JMLR 2021 Outside the Echo Chamber: Optimizing the Performative Risk ICML 2021 Overparameterization Improves Robustness to Covariate Shift in High Dimensions NeurIPS 2021 Predicting With Confidence on Unseen Distributions ICCV 2021 Representation Balancing Offline Model-based Reinforcement Learning ICLR 2021 Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data ICML 2021 Robust Generalization despite Distribution Shift via Minimum Discriminating Information NeurIPS 2021 Robustness and Adversarial Examples in Natural Language Processing EMNLP 2021 Robustness via Cross-Domain Ensembles ICCV 2021 Saliency is a Possible Red Herring When Diagnosing Poor Generalization ICLR 2021 Size-Invariant Graph Representations for Graph Classification Extrapolations ICML 2021 Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization NeurIPS 2021 The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization ICCV 2021 Towards a Theoretical Framework of Out-of-Distribution Generalization NeurIPS 2021 Towards Context-Agnostic Learning Using Synthetic Data NeurIPS 2021 Tradeoffs in Data Augmentation: An Empirical Study ICLR 2021 Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time NeurIPS 2021 TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? NeurIPS 2021 Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution NeurIPS 2021