Theory

A Precise Performance Analysis of Support Vector Regression ICML 2021 Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training NeurIPS 2021 A Review of Human Evaluation for Style Transfer ACL 2021 Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions ACL 2021 Are wider nets better given the same number of parameters? ICLR 2021 Artificial Text Detection via Examining the Topology of Attention Maps EMNLP 2021 A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs NeurIPS 2021 A Sharp Blockwise Tensor Perturbation Bound for Orthogonal Iteration JMLR 2021 Assessing Image and Text Generation With Topological Analysis and Fuzzy Logic WACV 2021 A Survey on Goal Recognition as Planning IJCAI 2021 Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models NeurIPS 2021 Asymptotics of Ridge Regression in Convolutional Models ICML 2021 A Theoretical Analysis of the Repetition Problem in Text Generation AAAI 2021 A Theory of Heuristic Learnability COLT 2021 A Theory of Independent Mechanisms for Extrapolation in Generative Models AAAI 2021 Attention Approximates Sparse Distributed Memory NeurIPS 2021 Attention is not all you need: pure attention loses rank doubly exponentially with depth ICML 2021 Attention is Turing-Complete JMLR 2021 A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021 A Uniform Abstraction Framework for Generalized Planning IJCAI 2021 A unifying view on implicit bias in training linear neural networks ICLR 2021 Average-Case Communication Complexity of Statistical Problems COLT 2021 Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks AAAI 2021 Banach Space Representer Theorems for Neural Networks and Ridge Splines JMLR 2021 Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms NeurIPS 2021