A Hölderian backtracking method for min-max and min-min problems

We present a new algorithm to solve min-max or min-min problems out of the convex world. We use rigidity assumptions, ubiquitous in learning, making our method applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us to devise a simple algo...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-07
Main Authors: Bolte, Jérôme, Glaudin, Lilian, Pauwels, Edouard, Serrurier, Mathieu
Format: Article
Language:English
Subjects:
Algorithms
Optimization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Bolte, Jérôme
Glaudin, Lilian
Pauwels, Edouard
Serrurier, Mathieu
description We present a new algorithm to solve min-max or min-min problems out of the convex world. We use rigidity assumptions, ubiquitous in learning, making our method applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us to devise a simple algorithm of ridge type. An original feature of our method is to come with automatic step size adaptation which departs from the usual overly cautious backtracking methods. In a general framework, we provide convergence theoretical guarantees and rates. We apply our findings on simple GAN problems obtaining promising numerical results.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2425463845</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2425463845</sourcerecordid><originalsourceid>FETCH-proquest_journals_24254638453</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwdFTwOLwtJyW1KDMxTyEpMTm7pAhIZOalK-SmlmTkpyik5Rcp5Gbm6eYmVigk5qVA2Jl5CgVF-Uk5qbnFPAysaYk5xam8UJqbQdnNNcTZQxeooLA0tbgkPiu_tCgPKBVvZGJkamJmbGFiakycKgCi0jms</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2425463845</pqid></control><display><type>article</type><title>A Hölderian backtracking method for min-max and min-min problems</title><source>Publicly Available Content Database</source><creator>Bolte, Jérôme ; Glaudin, Lilian ; Pauwels, Edouard ; Serrurier, Mathieu</creator><creatorcontrib>Bolte, Jérôme ; Glaudin, Lilian ; Pauwels, Edouard ; Serrurier, Mathieu</creatorcontrib><description>We present a new algorithm to solve min-max or min-min problems out of the convex world. We use rigidity assumptions, ubiquitous in learning, making our method applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us to devise a simple algorithm of ridge type. An original feature of our method is to come with automatic step size adaptation which departs from the usual overly cautious backtracking methods. In a general framework, we provide convergence theoretical guarantees and rates. We apply our findings on simple GAN problems obtaining promising numerical results.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Optimization</subject><ispartof>arXiv.org, 2020-07</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2425463845?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>778,782,25736,36995,44573</link.rule.ids></links><search><creatorcontrib>Bolte, Jérôme</creatorcontrib><creatorcontrib>Glaudin, Lilian</creatorcontrib><creatorcontrib>Pauwels, Edouard</creatorcontrib><creatorcontrib>Serrurier, Mathieu</creatorcontrib><title>A Hölderian backtracking method for min-max and min-min problems</title><title>arXiv.org</title><description>We present a new algorithm to solve min-max or min-min problems out of the convex world. We use rigidity assumptions, ubiquitous in learning, making our method applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us to devise a simple algorithm of ridge type. An original feature of our method is to come with automatic step size adaptation which departs from the usual overly cautious backtracking methods. In a general framework, we provide convergence theoretical guarantees and rates. We apply our findings on simple GAN problems obtaining promising numerical results.</description><subject>Algorithms</subject><subject>Optimization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwdFTwOLwtJyW1KDMxTyEpMTm7pAhIZOalK-SmlmTkpyik5Rcp5Gbm6eYmVigk5qVA2Jl5CgVF-Uk5qbnFPAysaYk5xam8UJqbQdnNNcTZQxeooLA0tbgkPiu_tCgPKBVvZGJkamJmbGFiakycKgCi0jms</recordid><startdate>20200717</startdate><enddate>20200717</enddate><creator>Bolte, Jérôme</creator><creator>Glaudin, Lilian</creator><creator>Pauwels, Edouard</creator><creator>Serrurier, Mathieu</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200717</creationdate><title>A Hölderian backtracking method for min-max and min-min problems</title><author>Bolte, Jérôme ; Glaudin, Lilian ; Pauwels, Edouard ; Serrurier, Mathieu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24254638453</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Bolte, Jérôme</creatorcontrib><creatorcontrib>Glaudin, Lilian</creatorcontrib><creatorcontrib>Pauwels, Edouard</creatorcontrib><creatorcontrib>Serrurier, Mathieu</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bolte, Jérôme</au><au>Glaudin, Lilian</au><au>Pauwels, Edouard</au><au>Serrurier, Mathieu</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Hölderian backtracking method for min-max and min-min problems</atitle><jtitle>arXiv.org</jtitle><date>2020-07-17</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>We present a new algorithm to solve min-max or min-min problems out of the convex world. We use rigidity assumptions, ubiquitous in learning, making our method applicable to many optimization problems. Our approach takes advantage of hidden regularity properties and allows us to devise a simple algorithm of ridge type. An original feature of our method is to come with automatic step size adaptation which departs from the usual overly cautious backtracking methods. In a general framework, we provide convergence theoretical guarantees and rates. We apply our findings on simple GAN problems obtaining promising numerical results.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2425463845
source Publicly Available Content Database
subjects Algorithms
Optimization
title A Hölderian backtracking method for min-max and min-min problems
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T04%3A32%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20H%C3%B6lderian%20backtracking%20method%20for%20min-max%20and%20min-min%20problems&rft.jtitle=arXiv.org&rft.au=Bolte,%20J%C3%A9r%C3%B4me&rft.date=2020-07-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2425463845%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_24254638453%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2425463845&rft_id=info:pmid/&rfr_iscdi=true