Theory

When are dynamical systems learned from time series data statistically accurate? NeurIPS 2024 Where Do Large Learning Rates Lead Us? NeurIPS 2024 Why are Sensitive Functions Hard for Transformers? ACL 2024 Why Do We Need Weight Decay in Modern Deep Learning? NeurIPS 2024 Wide Two-Layer Networks can Learn from Adversarial Perturbations NeurIPS 2024 Your Transformer is Secretly Linear ACL 2024 Absolute Position Embedding Learns Sinusoid-like Waves for Attention Based on Relative Position EMNLP 2023 Agnostic Learning of General ReLU Activation Using Gradient Descent ICLR 2023 A Kernel-Based View of Language Model Fine-Tuning ICML 2023 A Law of Robustness beyond Isoperimetry ICML 2023 Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations CVPR 2023 (Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy NeurIPS 2023 A Modern Look at the Relationship between Sharpness and Generalization ICML 2023 Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime AISTATS 2023 Analyzing and Diagnosing Pose Estimation With Attributions CVPR 2023 Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels ICML 2023 A New Perspective On the Expressive Equivalence Between Graph Convolution and Attention Models ACML 2023 An Inductive Bias for Tabular Deep Learning NeurIPS 2023 An Operator Theoretic Approach for Analyzing Sequence Neural Networks AAAI 2023 Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input ICML 2023 A Spectral Theory of Neural Prediction and Alignment NeurIPS 2023 Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023 Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization COLT 2023 Benign overfitting in ridge regression JMLR 2023 Benign Overfitting in Two-layer ReLU Convolutional Neural Networks ICML 2023