A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning

Abstract

Distributed learning aims at computing high-quality models by training over scattered data. This covers a diversity of scenarios, including computer clusters or mobile agents. One of the main challenges is then to deal with heterogeneous machines and unreliable communications. In this setting, we propose and analyze a flexible asynchronous optimization algorithm for solving nonsmooth learning problems. Unlike most existing methods, our algorithm is adjustable to various levels of communication costs, machines computational powers, and data distribution evenness. We prove that the algorithm converges linearly with a fixed learning rate that does not depend on communication delays nor on the number of machines. Although long delays in communication may slow down performance, no delay can break convergence.
No file

Dates and versions

hal-01996562 , version 1 (28-01-2019)

Identifiers

  • HAL Id : hal-01996562 , version 1

Cite

Konstantin Mishchenko, Franck Iutzeler, Jérôme Malick, Massih-Reza Amini. A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning. International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.3587-3595. ⟨hal-01996562⟩
75 View
0 Download

Share

Gmail Facebook X LinkedIn More