eprintid: 4985
rev_number: 19
eprint_status: archive
userid: 351
dir: disk0/00/00/49/85
datestamp: 2016-01-15 02:08:05
lastmod: 2021-08-27 17:15:48
status_changed: 2016-01-15 02:08:05
type: monograph
metadata_visibility: show
item_issues_count: 2
creators_name: Robinson, S.M.
title: Linear Convergence of Epsilon-Subgradient Descent Methods for a Class of Convex Functions
ispublished: pub
internal_subjects: iis_met
internal_subjects: iis_sys
divisions: prog_opt
abstract: This paper establishes a linear convergence rate for a class of epsilon-subgradient descent methods for minimizing certain convex functions.  Currently prominent methods belonging to this class include the resolvent (proximal point) method and the bundle method in proximal form (considered as a sequence of serious steps). Other methods, such as the recently proposed descent proximal level method, may also fit this framework depending on implementation. The convex functions covered by the analysis are those whose conjugates have subdifferentials that are locally upper Lipschitzian at the origin, a class introduced by Zhang and Treiman. We argue that this class is a natural candidate for study in connection with minimization algorithms.
date: 1996-04
date_type: published
publisher: WP-96-041
iiasapubid: WP-96-041
price: 10
full_text_status: public
monograph_type: working_paper
place_of_pub: IIASA, Laxenburg, Austria
pages: 11
coversheets_dirty: FALSE
fp7_type: info:eu-repo/semantics/book
citation:   Robinson, S.M.  (1996).  Linear Convergence of Epsilon-Subgradient Descent Methods for a Class of Convex Functions.   IIASA Working Paper. IIASA, Laxenburg, Austria: WP-96-041     
document_url: https://pure.iiasa.ac.at/id/eprint/4985/1/WP-96-041.pdf