Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods
Name
16m1094415.pdf
Description
Published version
Size
435.33 KB
Format
Adobe PDF
Checksum (MD5)
07c4155a1fd9c8e616d8b4337dbbeced
Author(s)
Vanli, Nuri Denizcan
Gurbuzbalaban, Mert
Ozdaglar, Asuman E
Date Issued
May 18, 2018
Publisher
Society for Industrial & Applied Mathematics (SIAM)
Citation
Vanli, N. D., et al. “Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods.” SIAM Journal on Optimization 28, no. 2, (January 2018): 1282–300. © 2018 Society for Industrial and Applied Mathematics
Version
Final published version
Abstract
We focus on the problem of minimizing the sum of smooth component functions (where the sum is strongly convex) and a nonsmooth convex function, which arises in regularized empirical risk minimization in machine learning and distributed constrained optimization in wireless sensor networks and smart grids. We consider solving this problem using the proximal incremental aggregated gradient (PIAG) method, which at each iteration moves along an aggregated gradient (formed by incrementally updating gradients of component functions according to a deterministic order) and takes a proximal step with respect to the nonsmooth function. While the convergence properties of this method with randomized orders (in updating gradients of component functions) have been investigated, this paper, to the best of our knowledge, is the first study that establishes the convergence rate properties of the PIAG method for any deterministic order. In particular, we show that the PIAG algorithm is globally convergent with a linear rate provided that the step size is sufficiently small. We explicitly identify the rate of convergence and the corresponding step size to achieve this convergence rate. Our results improve upon the best known condition number and gradient delay bound dependence of the convergence rate of the incremental aggregated gradient methods used for minimizing a sum of smooth functions. Key words. convex optimization, nonsmooth optimization, proximal incremental aggregated gradient method
MIT Department
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1137/16m1094415
