Theory

Local Identifiability of Deep ReLU Neural Networks: the Theory NeurIPS 2022 Locally Sparse Neural Networks for Tabular Biomedical Data ICML 2022 LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness NeurIPS 2022 Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks JMLR 2022 Measures of Information Reflect Memorization Patterns NeurIPS 2022 Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022 Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization NeurIPS 2022 Minimizing Control for Credit Assignment with Strong Feedback ICML 2022 More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize ICML 2022 Most Activation Functions Can Win the Lottery Without Excessive Depth NeurIPS 2022 Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path ICLR 2022 Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold NeurIPS 2022 Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules NeurIPS 2022 Neural Network Architecture Beyond Width and Depth NeurIPS 2022 Neural Networks can Learn Representations with Gradient Descent COLT 2022 Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective ICML 2022 Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs NeurIPS 2022 Neural Tangent Kernel Analysis of Deep Narrow Neural Networks ICML 2022 Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization ICML 2022 Non-Gaussian Tensor Programs NeurIPS 2022 ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation ACL 2022 On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds NeurIPS 2022 On global convergence of ResNets: From finite to infinite width using linear parameterization NeurIPS 2022 On Isotropy Calibration of Transformer Models ACL 2022 On Measuring Excess Capacity in Neural Networks NeurIPS 2022