paper-with-me

Papers

Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency

2021-02-25 · Yuyang Deng, Mehrdad Mahdavi

Local SGD is a promising approach to overcome the communication overhead in distributed learning by reducing the synchronization frequency among worker nodes. Despite the recent theoretical advances of local SGD in empirical risk minimization, the efficiency of its counterpart in minimax optimization remains unexplored. Motivated by large scale minimax learning problems, such as adversarial robust learning and training generative adversarial networks (GANs), we propose local Stochastic Gradient Descent Ascent (local SGDA), where the primal and dual variables can be trained locally and averaged periodically to significantly reduce the number of communications. We show that local SGDA can provably optimize distributed minimax problems in both homogeneous and heterogeneous data with reduced number of communications and establish convergence rates under strongly-convex-strongly-concave and nonconvex-strongly-concave settings. In addition, we propose a novel variant local SGDA+, to solve nonconvex-nonconcave problems. We give corroborating empirical evidence on different distributed minimax problems.

📄 PDF Abstract BibTeX arXiv:2102.13152

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Local SGD Local SGD is a distributed training technique that runs SGD independently in parallel on different workers and averages the sequences…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation

2020-09-30 · ICLR 2021 1 · Tanner Fiez, Lillian Ratliff

We study the role that a finite timescale separation parameter $\tau$ has on gradient descent-ascent in two-player non-convex, non-concave zero-sum games where the learning rate of player 1 is denoted by $\gamma_1$ and t…

A Communication-efficient Algorithm with Linear Convergence for Federated Minimax Learning

2022-06-02 · Zhenyu Sun, Ermin Wei

In this paper, we study a large-scale multi-agent minimax optimization problem, which models many interesting applications in statistical learning and game theory, including Generative Adversarial Networks (GANs). The ov…

Generalization Bounds

Accelerating Stochastic Gradient Descent using Predictive Variance Reduction

2013-12-01 · NeurIPS 2013 12 · Rie Johnson, Tong Zhang

Stochastic gradient descent is popular for large scale optimization but has slow convergence asymptotically due to the inherent variance. To remedy this problem, we introduce an explicit variance reduction method for sto…

Structured Prediction

Projected Push-Sum Gradient Descent-Ascent for Convex Optimizationwith Application to Economic Dispatch Problems

2020-08-11

We propose a novel algorithm for solving convex, constrained and distributed optimization problems defined on multi-agent-networks, where each agent has exclusive access to a part of the global objective function. The ag…

Distributed Optimization

Randomized Stochastic Gradient Descent Ascent

2021-11-25 · Othmane Sebbouh, Marco Cuturi, Gabriel Peyré

An increasing number of machine learning problems, such as robust or adversarial variants of existing algorithms, require minimizing a loss function that is itself defined as a maximum. Carrying a loop of stochastic grad…