gradient flow

Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks ICLR 2022 Improving Mini-batch Optimal Transport via Partial Transportation ICML 2022 Learning single-index models with shallow neural networks NeurIPS 2022 Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks JMLR 2022 MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning AAAI 2022 Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path ICLR 2022 Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again NeurIPS 2022 On feature learning in neural networks with global convergence guarantees ICLR 2022 On Margin Maximization in Linear and ReLU Networks NeurIPS 2022 On Non-local Convergence Analysis of Deep Linear Networks ICML 2022 On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NeurIPS 2022 On the inductive bias of neural networks for learning read-once DNFs UAI 2022 On Transportation of Mini-batches: A Hierarchical Approach ICML 2022 Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks NeurIPS 2022 The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program ICLR 2022 The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks JMLR 2022 Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis NeurIPS 2022 Training invariances and the low-rank phenomenon: beyond linear networks ICLR 2022 Variational Wasserstein gradient flow ICML 2022 Winning the Lottery Ahead of Time: Efficient Early Network Pruning ICML 2022 You Only Need One Model for Open-domain Question Answering EMNLP 2022 A Gradient Flow Framework For Analyzing Network Pruning ICLR 2021 A unifying view on implicit bias in training linear neural networks ICLR 2021 Continuous vs. Discrete Optimization of Deep Neural Networks NeurIPS 2021 Curriculum Learning by Optimizing Learning Dynamics AISTATS 2021