paper-with-me

Papers

A Decentralized Proximal Point-type Method for Saddle Point Problems

2019-10-31 · Weijie Liu, Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil, Zebang Shen, Nenggan Zheng

In this paper, we focus on solving a class of constrained non-convex non-concave saddle point problems in a decentralized manner by a group of nodes in a network. Specifically, we assume that each node has access to a summand of a global objective function and nodes are allowed to exchange information only with their neighboring nodes. We propose a decentralized variant of the proximal point method for solving this problem. We show that when the objective function is $\rho$-weakly convex-weakly concave the iterates converge to approximate stationarity with a rate of $\mathcal{O}(1/\sqrt{T})$ where the approximation error depends linearly on $\sqrt{\rho}$. We further show that when the objective function satisfies the Minty VI condition (which generalizes the convex-concave case) we obtain convergence to stationarity with a rate of $\mathcal{O}(1/\sqrt{T})$. To the best of our knowledge, our proposed method is the first decentralized algorithm with theoretical guarantees for solving a non-convex non-concave decentralized saddle point problem. Our numerical results for training a general adversarial network (GAN) in a decentralized manner match our theoretical guarantees.

📄 PDF Abstract BibTeX arXiv:1910.14380

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Type Prediction

Similar Papers 제목 키워드 기반

Stochastic Gradient Methods with Compressed Communication for Decentralized Saddle Point Problems

2022-05-28 · Chhavi Sharma, Vishnu Narayanan, P. Balamurugan

We develop two compression based stochastic gradient algorithms to solve a class of non-smooth strongly convex-strongly concave saddle-point problems in a decentralized setting (without a central server). Our first algor…

A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach

2019-01-24 · Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil

In this paper we consider solving saddle point problems using two variants of Gradient Descent-Ascent algorithms, Extra-gradient (EG) and Optimistic Gradient Descent Ascent (OGDA) methods. We show that both of these algo…

Switch and Conquer: Efficient Algorithms By Switching Stochastic Gradient Oracles For Decentralized Saddle Point Problems

2023-09-02 · Chhavi Sharma, Vishnu Narayanan, P. Balamurugan

We consider a class of non-smooth strongly convex-strongly concave saddle point problems in a decentralized setting without a central server. To solve a consensus formulation of problems in this class, we develop an inex…

Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms

2021-02-04 · Minhui Huang

We propose perturbed proximal algorithms that can provably escape strict saddles for nonsmooth weakly convex functions. The main results are based on a novel characterization of $\epsilon$-approximate local minimum for n…

A Stochastic Proximal Point Algorithm for Saddle-Point Problems

2019-09-13 · Luo Luo, Cheng Chen, Yu-Jun Li, Guangzeng Xie 외

We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achiev…