paper-with-me

Papers

Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks

2018-07-01 · ICML 2018 7 · Mingyi Hong, Meisam Razaviyayn, Jason Lee

In this work, we study two first-order primal-dual based algorithms, the Gradient Primal-Dual Algorithm (GPDA) and the Gradient Alternating Direction Method of Multipliers (GADMM), for solving a class of linearly constrained non-convex optimization problems. We show that with random initialization of the primal and dual variables, both algorithms are able to compute second-order stationary solutions (ss2) with probability one. This is the first result showing that primal-dual algorithm is capable of finding ss2 when only using first-order information; it also extends the existing results for first-order, but {primal-only} algorithms. An important implication of our result is that it also gives rise to the first global convergence result to the ss2, for two classes of unconstrained distributed non-convex learning problems over multi-agent networks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Distributed Optimization

Similar Papers 제목 키워드 기반

Variance Reduced Policy Evaluation with Smooth Function Approximation

2019-12-01 · NeurIPS 2019 12 · Hoi-To Wai, Mingyi Hong, Zhuoran Yang, Zhaoran Wang 외

Policy evaluation with smooth and nonlinear function approximation has shown great potential for reinforcement learning. Compared to linear function approxi- mation, it allows for using a richer class of approximation fu…

Reinforcement Learning

A first-order primal-dual method with adaptivity to local smoothness

2021-10-28 · NeurIPS 2021 12 · Maria-Luiza Vladarean, Yura Malitsky, Volkan Cevher

We consider the problem of finding a saddle point for the convex-concave objective $\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y)$, where $f$ is a convex function with locally Lipschitz gradient and $g$ is convex an…

A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance

2025-05-07 · Axel Friedrich Wolter, Tobias Sutter

We study reinforcement learning by combining recent advances in regularized linear programming formulations with the classical theory of stochastic approximation. Motivated by the challenge of designing algorithms that l…

A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

2024-01-31 · Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara 외

We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms fo…

Reinforcement Learning (RL)

A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations

2024-11-09 · Shu Liu, Stanley Osher, Wuchen Li

We propose a scalable preconditioned primal-dual hybrid gradient algorithm for solving partial differential equations (PDEs). We multiply the PDE with a dual test function to obtain an inf-sup problem whose loss function…