Theory

When Does Optimizing a Proper Loss Yield Calibration? NeurIPS 2023 When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability NeurIPS 2023 When do Minimax-fair Learning and Empirical Risk Minimization Coincide? ICML 2023 When is Realizability Sufficient for Off-Policy Reinforcement Learning? ICML 2023 When Locally Linear Embedding Hits Boundary JMLR 2023 When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations MLHC 2023 Why Bother with Geometry? On the Relevance of Linear Decompositions of Transformer Embeddings EMNLP 2023 Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption AAAI 2023 "Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts ICML 2023 Why Out-of-Distribution detection experiments are not reliable - subtle experimental details muddle the OOD detector rankings UAI 2023 Why Target Networks Stabilise Temporal Difference Methods ICML 2023 Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously Interspeech 2023 Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models NeurIPS 2023 Width and Depth Limits Commute in Residual Networks ICML 2023 Window-Based Distribution Shift Detection for Deep Neural Networks NeurIPS 2023 WL meet VC ICML 2023 “World Knowledge” in Multiple Choice Reading Comprehension EACL 2023 Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding ICLR 2023 A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds AISTATS 2022 Accelerating Shapley Explanation via Contributive Cooperator Selection ICML 2022 A Classification of G-invariant Shallow Neural Networks NeurIPS 2022 ACL Tutorial Proposal: Towards Reproducible Machine Learning Research in Natural Language Processing ACL 2022 A Comparative Study of Faithfulness Metrics for Model Interpretability Methods ACL 2022 A Complete Characterisation of ReLU-Invariant Distributions AISTATS 2022 A Computable Definition of the Spectral Bias AAAI 2022