gradient descent

A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear Network ICML 2021 An algorithmic view of L2 regularization and some path-following algorithms JMLR 2021 Anderson acceleration of coordinate descent AISTATS 2021 An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning NeurIPS 2021 A Novel Sequential Coreset Method for Gradient Descent Algorithms ICML 2021 A Recipe for Global Convergence Guarantee in Deep Neural Networks AAAI 2021 A single gradient step finds adversarial examples on random two-layers neural networks NeurIPS 2021 A Study of Condition Numbers for First-Order Optimization AISTATS 2021 Asynchronous Decentralized Online Learning NeurIPS 2021 Asynchronous Stochastic Optimization Robust to Arbitrary Delays NeurIPS 2021 A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix AISTATS 2021 A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints JMLR 2021 Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach NeurIPS 2021 A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization ICML 2021 Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent NeurIPS 2021 Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods ICLR 2021 Better Training using Weight-Constrained Stochastic Dynamics ICML 2021 Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization EMNLP 2021 CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression NeurIPS 2021 Characterizing the implicit bias via a primal-dual analysis ALT 2021 Characterizing the Loss Landscape in Non-Negative Matrix Factorization AAAI 2021 Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems NeurIPS 2021 Computational Separation Between Convolutional and Fully-Connected Networks ICLR 2021 Conflict-Averse Gradient Descent for Multi-task learning NeurIPS 2021 Constrained labeling for weakly supervised learning UAI 2021