Work

An introduction to decentralized stochastic optimization with gradient tracking

Year: 2019
Type: preprint
Abstract: Decentralized solutions to finite-sum minimization are of significant importance in many signal processing, control, and machine learning applications. In such settings, the data is distributed over a network of arbitrarily-connected nodes and raw data sharing is prohibitive often due to communication or privacy constraints. In this article, we review decentralized stochastic first-order optimization methods and illustrate some recent improvements based on gradient tracking and variance reduction, focusing particularly on smooth and strongly-convex objective functions. We provide intuitive illustrations of the main technical ideas as well as applications of the algorithms in the context of decentralized training of machine learning models.
Language: English
Open Access status: green
OpenAlex ID: W2986633540
Cites: 55
Cited by: 11
Related to: 7