Theory

Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics ICLR 2023 Unlocking Deterministic Robustness Certification on ImageNet NeurIPS 2023 Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features ICML 2023 VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution CVPR 2023 What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models NeurIPS 2023 What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement. NeurIPS 2023 When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability NeurIPS 2023 Width and Depth Limits Commute in Residual Networks ICML 2023 Window-Based Distribution Shift Detection for Deep Neural Networks NeurIPS 2023 α-ReQ : Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay NeurIPS 2022 3DeformRS: Certifying Spatial Deformations on Point Clouds CVPR 2022 A Classification of G-invariant Shallow Neural Networks NeurIPS 2022 A Computable Definition of the Spectral Bias AAAI 2022 A Consistent and Differentiable Lp Canonical Calibration Error Estimator NeurIPS 2022 A Dynamical System Perspective for Lipschitz Neural Networks ICML 2022 A Fourier Approach to Mixture Learning NeurIPS 2022 AFRNN: Stable RNN with Top Down Feedback and Antisymmetry ACML 2022 A general approximation lower bound in L^p norm, with applications to feed-forward neural networks NeurIPS 2022 Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective NeurIPS 2022 Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability NeurIPS 2022 An empirical analysis of compute-optimal large language model training NeurIPS 2022 Annihilation of Spurious Minima in Two-Layer ReLU Networks NeurIPS 2022 A PAC-Bayesian Generalization Bound for Equivariant Networks NeurIPS 2022 A Practical, Progressively-Expressive GNN NeurIPS 2022 A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions JMLR 2022