Global convergence rate of incremental aggregated gradient methods for nonsmooth problems

Global convergence rate of incremental aggregated gradient methods for nonsmooth problems

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...

Full description

Bibliographic Details
Main Authors: Vanli, Nuri Denizcan, Gurbuzbalaban, Mert, Koksal, Asuman E.
Other Authors: Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Format: Article
Language:en_US
Published: Institute of Electrical and Electronics Engineers (IEEE) 2017
Online Access:http://hdl.handle.net/1721.1/111781
https://orcid.org/0000-0002-0575-2450
https://orcid.org/0000-0002-1827-1285

Internet

http://hdl.handle.net/1721.1/111781
https://orcid.org/0000-0002-0575-2450
https://orcid.org/0000-0002-1827-1285

Similar Items