paper-with-me

홈 › Papers

A Provably Communication-Efficient Asynchronous Distributed Inference Method for Convex and Nonconvex Problems

2019-03-16 · Jineng Ren, Jarvis Haupt

This paper proposes and analyzes a communication-efficient distributed optimization framework for general nonconvex nonsmooth signal processing and machine learning problems under an asynchronous protocol. At each iteration, worker machines compute gradients of a known empirical loss function using their own local data, and a master machine solves a related minimization problem to update the current estimate. We prove that for nonconvex nonsmooth problems, the proposed algorithm converges with a sublinear rate over the number of communication rounds, coinciding with the best theoretical rate that can be achieved for this class of problems. Linear convergence is established without any statistical assumptions of the local data for problems characterized by composite loss functions whose smooth parts are strongly convex. Extensive numerical experiments verify that the performance of the proposed approach indeed improves -- sometimes significantly -- over other state-of-the-art algorithms in terms of total communication efficiency.

📄 PDF Abstract BibTeX arXiv:1903.06871

Code (0)

등록된 구현이 없습니다.

Tasks

Distributed Optimization

Similar Papers 제목 키워드 기반

Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity

2024-02-07 · Alexander Tyurin, Marta Pozzi, Ivan Ilin, Peter Richtárik

We consider nonconvex stochastic optimization problems in the asynchronous centralized distributed setup where the communication times from workers to a server can not be ignored, and the computation and communication ti…

Stochastic Optimization

On Parallel or Distributed Asynchronous Iterations with Unbounded Delays and Possible Out of Order Messages or Flexible Communication for Convex Optimization Problems and Machine Learning

2022-10-05 · Didier El Baz

We describe several features of parallel or distributed asynchronous iterative algorithms such as unbounded delays, possible out of order messages or flexible communication. We concentrate on the concept of macroiteratio…

Survey

Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning

2025-09-29 · Alexander Tyurin, Andrei Spiridonov, Varvara Rudenko arxiv

We study distributed reinforcement learning (RL) with policy gradient methods under asynchronous and parallel computations and communications. While non-distributed methods are well understood theoretically and have achi…

Reinforcement Learning

Graph Neural Networks Gone Hogwild

2024-06-29 · Olga Solodova, Nick Richardson, Deniz Oktay, Ryan P. Adams

Message passing graph neural networks (GNNs) would appear to be powerful tools to learn distributed algorithms via gradient descent, but generate catastrophically incorrect predictions when nodes update asynchronously du…

Distributed Optimization

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates

2018-03-05 · ICML 2018 7 · Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbi…