paper-with-me

Papers

Optimal Algorithms for Decentralized Stochastic Variational Inequalities

2022-02-06 · Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander Gasnikov

Variational inequalities are a formalism that includes games, minimization, saddle point, and equilibrium problems as special cases. Methods for variational inequalities are therefore universal approaches for many applied tasks, including machine learning problems. This work concentrates on the decentralized setting, which is increasingly important but not well understood. In particular, we consider decentralized stochastic (sum-type) variational inequalities over fixed and time-varying networks. We present lower complexity bounds for both communication and local iterations and construct optimal algorithms that match these lower bounds. Our algorithms are the best among the available literature not only in the decentralized stochastic case, but also in the decentralized deterministic and non-distributed stochastic cases. Experimental results confirm the effectiveness of the presented algorithms.

📄 PDF Abstract BibTeX arXiv:2202.02771

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure

2023-09-21 · NeurIPS 2023 11

We consider the problem of solving stochastic monotone variational inequalities with a separable structure using a stochastic first-order oracle. Building on standard extragradient for variational inequalities we propose…

Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey

2022-08-29 · Aleksandr Beznosikov, Boris Polyak, Eduard Gorbunov, Dmitry Kovalev 외

This paper is a survey of methods for solving smooth (strongly) monotone stochastic variational inequalities. To begin with, we give the deterministic foundation from which the stochastic methods eventually evolved. Then…

Survey

Decentralized Local Stochastic Extra-Gradient for Variational Inequalities

2021-06-15 · Aleksandr Beznosikov, Pavel Dvurechensky, Anastasia Koloskova, Valentin Samokhin 외

We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the c…

Federated Learning

Adaptive and Universal Algorithms for Variational Inequalities with Optimal Convergence

2020-10-15 · Alina Ene, Huy L. Nguyen

We develop new adaptive algorithms for variational inequalities with monotone operators, which capture many problems of interest, notably convex optimization and convex-concave saddle point problems. Our algorithms autom…

Optimal Algorithms for Differentially Private Stochastic Monotone Variational Inequalities and Saddle-Point Problems

2021-04-07 · Digvijay Boob, Cristóbal Guzmán

In this work, we conduct the first systematic study of stochastic variational inequality (SVI) and stochastic saddle point (SSP) problems under the constraint of differential privacy (DP). We propose two algorithms: Nois…