Theory

Variational Gaussian Processes: A Functional Analysis View AISTATS 2022 Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes AAAI 2022 Versatile Dueling Bandits: Best-of-both World Analyses for Learning from Relative Preferences ICML 2022 Visualizing the Relationship Between Encoded Linguistic Information and Task Performance ACL 2022 Weak Separation in Mixture Models and Implications for Principal Stratification AISTATS 2022 Weisfeiler-Lehman Meets Gromov-Wasserstein ICML 2022 What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness? NeurIPS 2022 What Do We Mean by Generalization in Federated Learning? ICLR 2022 What is a Good Metric to Study Generalization of Minimax Learners? NeurIPS 2022 What You See is What You Get: Principled Deep Learning via Distributional Generalization NeurIPS 2022 When and How Mixup Improves Calibration ICML 2022 When Combinatorial Thompson Sampling meets Approximation Regret NeurIPS 2022 When Hardness of Approximation Meets Hardness of Learning JMLR 2022 When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits NeurIPS 2022 When to Update Your Model: Constrained Model-based Reinforcement Learning NeurIPS 2022 When Votes Change and Committees Should (Not) IJCAI 2022 Which Model is Best: Comparing Methods and Metrics for Automatic Laughter Detection in a Naturalistic Conversational Dataset Interspeech 2022 Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective ICLR 2022 White-box Testing of NLP models with Mask Neuron Coverage NAACL 2022 Why do tree-based models still outperform deep learning on typical tabular data? NeurIPS 2022 Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation ACL 2022 Why predicting risk can’t identify ‘risk factors’: empirical assessment of model stability in machine learning across observational health databases MLHC 2022 Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error ICML 2022 Width is Less Important than Depth in ReLU Neural Networks COLT 2022 WordTies: Measuring Word Associations in Language Models via Constrained Sampling EMNLP 2022