first-order method

On Acceleration for Convex Composite Minimization with Noise-Corrupted Gradients and Approximate Proximal Mapping JMLR 2022 On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems JMLR 2022 Optimal and Adaptive Monteiro-Svaiter Acceleration NeurIPS 2022 Practical Schemes for Finding Near-Stationary Points of Convex Finite-Sums AISTATS 2022 Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusions NeurIPS 2022 Super-Acceleration with Cyclical Step-sizes AISTATS 2022 Accelerating Quadratic Optimization with Reinforcement Learning NeurIPS 2021 Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz Requirements NeurIPS 2021 Adversarial Regression with Doubly Non-negative Weighting Matrices NeurIPS 2021 A first-order primal-dual method with adaptivity to local smoothness NeurIPS 2021 Anderson acceleration of coordinate descent AISTATS 2021 A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints JMLR 2021 Average-case Acceleration for Bilinear Games and Normal Matrices ICLR 2021 Convex-Concave Min-Max Stackelberg Games NeurIPS 2021 Debiasing a First-order Heuristic for Approximate Bi-level Optimization ICML 2021 First-Order Methods for Wasserstein Distributionally Robust MDP ICML 2021 Increasing Iterate Averaging for Solving Saddle-Point Problems AAAI 2021 Momentum Improves Optimization on Riemannian Manifolds AISTATS 2021 On a Combination of Alternating Minimization and Nesterov’s Momentum ICML 2021 Practical Large-Scale Linear Programming using Primal-Dual Hybrid Gradient NeurIPS 2021 Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization AISTATS 2021 Scalable First-Order Methods for Robust MDPs AAAI 2021 Sifting through the noise: Universal first-order methods for stochastic variational inequalities NeurIPS 2021 A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization NeurIPS 2020 Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates NeurIPS 2020