Theory

The Influence of Dimensions on the Complexity of Computing Decision Trees AAAI 2023 The Lie Derivative for Measuring Learned Equivariance ICLR 2023 The Many Faces of Adversarial Machine Learning AAAI 2023 The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data NeurIPS 2023 The Numerical Stability of Hyperbolic Representation Learning ICML 2023 The OPUS-MT Dashboard – A Toolkit for a Systematic Evaluation of Open Machine Translation Models ACL 2023 Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks NeurIPS 2023 Theoretical and Numerical Analysis of 3D Reconstruction Using Point and Line Incidences ICCV 2023 Theoretical and Practical Perspectives on what Influence Functions Do NeurIPS 2023 Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks EACL 2023 Theory on Forgetting and Generalization of Continual Learning ICML 2023 The Parameterized Complexity of Finding Concise Local Explanations IJCAI 2023 The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications AAAI 2023 The Power of Recursion in Graph Neural Networks for Counting Substructures AISTATS 2023 The Regret of Exploration and the Control of Bad Episodes in Reinforcement Learning ICML 2023 The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit NeurIPS 2023 The Shrinkage-Delinkage Trade-off: an Analysis of Factorized Gaussian Approximations for Variational Inference UAI 2023 The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation ICML 2023 The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium ICLR 2023 The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning ICML 2023 Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points NeurIPS 2023 Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration EMNLP 2023 Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations ICML 2023 Tight Data Access Bounds for Private Top-k Selection ICML 2023 Tighter Analysis for ProxSkip ICML 2023