Journals
Resources
About Us
Open Access

Parallel Stochastic Newton Method

Parallel Stochastic Newton Method

Year:    2018

Author:    Mojmír Mutný, Peter Richtárik

Journal of Computational Mathematics, Vol. 36 (2018), Iss. 3 : pp. 404–425

Abstract

We propose a parallel stochastic Newton method (PSN) for minimizing unconstrained smooth convex functions. We analyze the method in the strongly convex case, and give conditions under which acceleration can be expected when compared to its serial counterpart. We show how PSN can be applied to the large quadratic function minimization in general, and empirical risk minimization problems. We demonstrate the practical efficiency of the method through numerical experiments and models of simple matrix classes.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/jcm.1708-m2017-0113

Journal of Computational Mathematics, Vol. 36 (2018), Iss. 3 : pp. 404–425

Published online:    2018-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    22

Keywords:    optimization parallel methods Newton's method stochastic algorithms.

Author Details

Mojmír Mutný

Peter Richtárik

  1. Use of Projective Coordinate Descent in the Fekete Problem

    Polyak, B. T. | Fatkhullin, I. F.

    Computational Mathematics and Mathematical Physics, Vol. 60 (2020), Iss. 5 P.795

    https://doi.org/10.1134/S0965542520050127 [Citations: 1]
  2. Stochastic Reformulations of Linear Systems: Algorithms and Convergence Theory

    Richtárik, Peter | Takáč, Martin

    SIAM Journal on Matrix Analysis and Applications, Vol. 41 (2020), Iss. 2 P.487

    https://doi.org/10.1137/18M1179249 [Citations: 31]
  3. On the local convergence of a stochastic semismooth Newton method for nonsmooth nonconvex optimization

    Milzarek, Andre | Xiao, Xiantao | Wen, Zaiwen | Ulbrich, Michael

    Science China Mathematics, Vol. 65 (2022), Iss. 10 P.2151

    https://doi.org/10.1007/s11425-020-1865-1 [Citations: 3]