Theory

Positional Encoding As Spatial Inductive Bias in GANs CVPR 2021 Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021 Provable Lipschitz Certification for Generative Models ICML 2021 Provable Memorization via Deep Neural Networks using Sub-linear Parameters COLT 2021 Provably Strict Generalisation Benefit for Equivariant Models ICML 2021 Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels ICML 2021 Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021 Relating Adversarially Robust Generalization to Flat Minima ICCV 2021 Relative Flatness and Generalization NeurIPS 2021 Representational aspects of depth and conditioning in normalizing flows ICML 2021 Representation Costs of Linear Neural Networks: Analysis and Design NeurIPS 2021 Rethinking the Variational Interpretation of Accelerated Optimization Methods NeurIPS 2021 Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs IJCAI 2021 Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021 Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021 Scalable Partial Explainability in Neural Networks via Flexible Activation Functions (Student Abstract) AAAI 2021 Scalable Verification of Quantized Neural Networks AAAI 2021 Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification NeurIPS 2021 Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics NeurIPS 2021 Size and Depth Separation in Approximating Benign Functions with Neural Networks COLT 2021 SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation ICML 2021 Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration NeurIPS 2021 Stateful ODE-Nets using Basis Function Expansions NeurIPS 2021 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics ICML 2021 Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks ICML 2021