distributional shift

Offline-to-Online Co-Evolutional User Simulator and Dialogue System EMNLP 2022 Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks ICML 2022 Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms AAAI 2022 Robustness Guarantees for Credal Bayesian Networks via Constraint Relaxation over Probabilistic Circuits IJCAI 2022 S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning NeurIPS 2022 Continual Quality Estimation with Online Bayesian Meta-Learning ACL 2021 Dealing with the Unknown: Pessimistic Offline Reinforcement Learning CoRL 2021 Heterogeneous Risk Minimization ICML 2021 Learning to Perturb Word Embeddings for Out-of-distribution QA ACL 2021 Offline Reinforcement Learning with Reverse Model-based Imagination NeurIPS 2021 On Robustness and Transferability of Convolutional Neural Networks CVPR 2021 On the Importance of Gradients for Detecting Distributional Shifts in the Wild NeurIPS 2021 OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning ICLR 2021 OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation ICML 2021 Out-of-Distribution Generalization via Risk Extrapolation (REx) ICML 2021 Recovering Latent Causal Factor for Generalization to Distributional Shifts NeurIPS 2021 Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data NeurIPS 2021 Stable Adversarial Learning under Distributional Shifts AAAI 2021 Conservative Q-Learning for Offline Reinforcement Learning NeurIPS 2020 Distributionally Robust Bayesian Optimization AISTATS 2020 Improving model calibration with accuracy versus uncertainty optimization NeurIPS 2020 MOPO: Model-based Offline Policy Optimization NeurIPS 2020 What went wrong and when? Instance-wise feature importance for time-series black-box models NeurIPS 2020 Addressing Model Vulnerability to Distributional Shifts Over Image Transformation Sets ICCV 2019 Causal Confusion in Imitation Learning NeurIPS 2019