Global convergence rate of incremental aggregated gradient methods for nonsmooth problems
Name
Ozdaglar_Global convergence.pdf
Size
230.5 KB
Format
Adobe PDF
Checksum (MD5)
b2770e4ddeea857b9569c869facab4b6
Author(s)
Vanli, Nuri Denizcan
Gurbuzbalaban, Mert
Koksal, Asuman E.
Date Issued
December 2016
Journal
2016 IEEE 55th Conference on Decision and Control (CDC)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Vanli, N. Denizcan et al. “Global Convergence Rate of Incremental Aggregated Gradient Methods for Nonsmooth Problems.” 2016 IEEE 55th Conference on Decision and Control (CDC), December 12-14 2016, Las Vegas, Nevada, USA, Institute of Electrical and Electronics Engineers (IEEE), December 2016: 173-178 © 2016 Institute of Electrical and Electronics Engineers (IEEE)
Version
Original manuscript
Abstract
We analyze the proximal incremental aggregated gradient (PIAG) method for minimizing the sum of a large number of smooth component functions f(x) = Σ[subscript i=1]m f[subscript i](x) and a convex function r(x). Such composite optimization problems arise in a number of machine learning applications including regularized regression problems and constrained distributed optimization problems over sensor networks. Our method computes an approximate gradient for the function f(x) by aggregating the component gradients evaluated at outdated iterates over a finite window K and uses a proximal operator with respect to the regularization function r(x) at the intermediate iterate obtained by moving along the approximate gradient. Under the assumptions that f(x) is strongly convex and each f[subscript i](x) is smooth with Lipschitz gradients, we show the first linear convergence rate result for the PIAG method and provide explicit convergence rate estimates that highlight the dependence on the condition number of the problem and the size of the window K over which outdated component gradients are evaluated.
MIT Department
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CDC.2016.7798265
