Open Access
Translator Disclaimer
2018 Stochastic heavy ball
Sébastien Gadat, Fabien Panloup, Sofiane Saadane
Electron. J. Statist. 12(1): 461-529 (2018). DOI: 10.1214/18-EJS1395

Abstract

This paper deals with a natural stochastic optimization procedure derived from the so-called Heavy-ball method differential equation, which was introduced by Polyak in the 1960s with his seminal contribution [Pol64]. The Heavy-ball method is a second-order dynamics that was investigated to minimize convex functions $f$. The family of second-order methods recently received a large amount of attention, until the famous contribution of Nesterov [Nes83], leading to the explosion of large-scale optimization problems. This work provides an in-depth description of the stochastic heavy-ball method, which is an adaptation of the deterministic one when only unbiased evalutions of the gradient are available and used throughout the iterations of the algorithm. We first describe some almost sure convergence results in the case of general non-convex coercive functions $f$. We then examine the situation of convex and strongly convex potentials and derive some non-asymptotic results about the stochastic heavy-ball method. We end our study with limit theorems on several rescaled algorithms.

Citation

Download Citation

Sébastien Gadat. Fabien Panloup. Sofiane Saadane. "Stochastic heavy ball." Electron. J. Statist. 12 (1) 461 - 529, 2018. https://doi.org/10.1214/18-EJS1395

Information

Received: 1 September 2016; Published: 2018
First available in Project Euclid: 19 February 2018

zbMATH: 06841011
MathSciNet: MR3765604
Digital Object Identifier: 10.1214/18-EJS1395

Subjects:
Primary: 35H10 , 35P15 , 60G15 , 60J70

Keywords: Random dynamical systems , second-order methods , Stochastic optimization algorithms

JOURNAL ARTICLE
69 PAGES


SHARE
Vol.12 • No. 1 • 2018
Back to Top