gradient flow

Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity NeurIPS 2021 Improving Gradient Flow with Unrolled Highway Expectation Maximization AAAI 2021 KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support NeurIPS 2021 Learning Node Representations Using Stationary Flow Prediction on Large Payment and Cash Transaction Networks ICML 2021 Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent AISTATS 2021 Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model NeurIPS 2021 On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent ICML 2021 On the Origin of Implicit Regularization in Stochastic Gradient Descent ICLR 2021 Orthogonalizing Convolutional Layers with the Cayley Transform ICLR 2021 Path Length Bounds for Gradient Descent and Flow JMLR 2021 Refining Deep Generative Models via Discriminator Gradient Flow ICLR 2021 Sampling with Trusthworthy Constraints: A Variational Gradient Framework NeurIPS 2021 Skew-symmetrically perturbed gradient flow for convex optimization ACML 2021 The inductive bias of ReLU networks on orthogonally separable data ICLR 2021 Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning ICLR 2021 Understanding Deflation Process in Over-parametrized Tensor Decomposition NeurIPS 2021 Understanding the Dynamics of Gradient Flow in Overparameterized Linear models ICML 2021 Approximate Inference with Wasserstein Gradient Flows AISTATS 2020 Black-Box Variational Inference as a Parametric Approximation to Langevin Dynamics ICML 2020 Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval NeurIPS 2020 Directional convergence and alignment in deep learning NeurIPS 2020 Finite-Time Convergence in Continuous-Time Optimization ICML 2020 Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint ICLR 2020 How to Trap a Gradient Flow COLT 2020 Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NeurIPS 2020