implicit regularization

SGD with Large Step Sizes Learns Sparse Features ICML 2023 Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems COLT 2023 The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent ICML 2023 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023 Actor-critic is implicitly biased towards high entropy optimal policies ICLR 2022 Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent NeurIPS 2022 Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks NeurIPS 2022 Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization ICLR 2022 Does Momentum Change the Implicit Regularization on Separable Data? NeurIPS 2022 DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization ICLR 2022 Energy-Based Latent Aligner for Incremental Learning CVPR 2022 Implicit Gradient Alignment in Distributed and Federated Learning AAAI 2022 Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks ICML 2022 Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions NeurIPS 2022 Implicit Regularization with Polynomial Growth in Deep Tensor Factorization ICML 2022 Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm COLT 2022 Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably AISTATS 2022 On the Frequency-bias of Coordinate-MLPs NeurIPS 2022 Robust Training under Label Noise by Over-parameterization ICML 2022 STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing EMNLP 2022 Stochastic Training is Not Necessary for Generalization ICLR 2022 Strength of Minibatch Noise in SGD ICLR 2022 The alignment property of SGD noise and how it helps select flat minima: A stability analysis NeurIPS 2022 Understanding Gradient Descent on the Edge of Stability in Deep Learning ICML 2022 Why neural networks find simple solutions: The many regularizers of geometric complexity NeurIPS 2022