Modified Fejér sequences and applications

In this note, we propose and study the notion of modified Fejér sequences. Within a Hilbert space setting, this property has been used to prove ergodic convergence of proximal incremental subgradient methods. Here we show that indeed it provides a unifying framework to prove convergence rates for ob...

Full description

Bibliographic Details
Main Authors: Lin, Junhong, Rosasco, Lorenzo, Villa, Silvia, Zhou, Ding-Xuan
Other Authors: Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Format: Article
Language:English
Published: Springer US 2018
Online Access:http://hdl.handle.net/1721.1/117359
https://orcid.org/0000-0001-6376-4786
_version_ 1826201333453029376
author Lin, Junhong
Rosasco, Lorenzo
Villa, Silvia
Zhou, Ding-Xuan
author2 Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
author_facet Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Lin, Junhong
Rosasco, Lorenzo
Villa, Silvia
Zhou, Ding-Xuan
author_sort Lin, Junhong
collection MIT
description In this note, we propose and study the notion of modified Fejér sequences. Within a Hilbert space setting, this property has been used to prove ergodic convergence of proximal incremental subgradient methods. Here we show that indeed it provides a unifying framework to prove convergence rates for objective function values of several optimization algorithms. In particular, our results apply to forward–backward splitting algorithm, incremental subgradient proximal algorithm, and the Douglas–Rachford splitting method including and generalizing known results.
first_indexed 2024-09-23T11:49:58Z
format Article
id mit-1721.1/117359
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T11:49:58Z
publishDate 2018
publisher Springer US
record_format dspace
spelling mit-1721.1/1173592022-10-01T06:21:16Z Modified Fejér sequences and applications Lin, Junhong Rosasco, Lorenzo Villa, Silvia Zhou, Ding-Xuan Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Rosasco, Lorenzo In this note, we propose and study the notion of modified Fejér sequences. Within a Hilbert space setting, this property has been used to prove ergodic convergence of proximal incremental subgradient methods. Here we show that indeed it provides a unifying framework to prove convergence rates for objective function values of several optimization algorithms. In particular, our results apply to forward–backward splitting algorithm, incremental subgradient proximal algorithm, and the Douglas–Rachford splitting method including and generalizing known results. Italy. Ministry of Education, University, Scientific and Technological Research (FIRB Project RBFR12M3AC) 2018-08-14T17:52:33Z 2018-09-02T05:00:05Z 2017-11 2018-08-08T04:08:09Z Article http://purl.org/eprint/type/JournalArticle 0926-6003 1573-2894 http://hdl.handle.net/1721.1/117359 Lin, Junhong, et al. “Modified Fejér Sequences and Applications.” Computational Optimization and Applications, vol. 71, no. 1, Sept. 2018, pp. 95–113. https://orcid.org/0000-0001-6376-4786 en https://doi.org/10.1007/s10589-017-9962-1 Computational Optimization and Applications 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. Springer Science+Business Media, LLC application/pdf Springer US Springer US
spellingShingle Lin, Junhong
Rosasco, Lorenzo
Villa, Silvia
Zhou, Ding-Xuan
Modified Fejér sequences and applications
title Modified Fejér sequences and applications
title_full Modified Fejér sequences and applications
title_fullStr Modified Fejér sequences and applications
title_full_unstemmed Modified Fejér sequences and applications
title_short Modified Fejér sequences and applications
title_sort modified fejer sequences and applications
url http://hdl.handle.net/1721.1/117359
https://orcid.org/0000-0001-6376-4786
work_keys_str_mv AT linjunhong modifiedfejersequencesandapplications
AT rosascolorenzo modifiedfejersequencesandapplications
AT villasilvia modifiedfejersequencesandapplications
AT zhoudingxuan modifiedfejersequencesandapplications