Robustness

Learning GMMs with Nearly Optimal Robustness Guarantees COLT 2022 Learning Recourse on Instance Environment to Enhance Prediction Accuracy NeurIPS 2022 Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization AAAI 2022 LOG: Active Model Adaptation for Label-Efficient OOD Generalization NeurIPS 2022 Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering EMNLP 2022 LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness NeurIPS 2022 Maximum Entropy RL (Provably) Solves Some Robust RL Problems ICLR 2022 Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification NeurIPS 2022 Measuring Harmful Representations in Scandinavian Language Models EMNLP 2022 MINIMAL: Mining Models for Universal Adversarial Triggers AAAI 2022 Models Out of Line: A Fourier Lens on Distribution Shift Robustness NeurIPS 2022 Noise-Robust Learning from Multiple Unsupervised Sources of Inferred Labels AAAI 2022 On Optimal Learning Under Targeted Data Poisoning NeurIPS 2022 On Robust Multiclass Learnability NeurIPS 2022 On the Adversarial Robustness of Mixture of Experts NeurIPS 2022 On the Robustness of Graph Neural Diffusion to Topology Perturbations NeurIPS 2022 On the Strong Correlation Between Model Invariance and Generalization NeurIPS 2022 Optimizing Relevance Maps of Vision Transformers Improves Robustness NeurIPS 2022 Outlier-Robust Sparse Estimation via Non-Convex Optimization NeurIPS 2022 Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributions NeurIPS 2022 Pay attention to your loss : understanding misconceptions about Lipschitz neural networks NeurIPS 2022 Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness NeurIPS 2022 Phase Transition from Clean Training to Adversarial Training NeurIPS 2022 Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model AAAI 2022 Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NeurIPS 2022