A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees

We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the scheme yields so-called coreset results for various Machine Learning problems including 1-median, Balanced Development, Spar...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-08
Main Authors: Ravi, Sathya N, Collins, Maxwell D, Singh, Vikas
Format: Article
Language:English
Subjects:
Algorithms
Data analysis
Machine learning
Support vector machines
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 Ravi, Sathya N
Collins, Maxwell D
Singh, Vikas
description We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the scheme yields so-called coreset results for various Machine Learning problems including 1-median, Balanced Development, Sparse PCA, Graph Cuts, and the \(\ell_1\)-norm-regularized Support Vector Machine (SVM) among others. This means that the algorithm provides approximate solutions to these problems in time complexity bounds that are not dependent on the size of the input problem. Our framework, motivated by a growing body of work on sublinear algorithms for various data analysis problems, is entirely deterministic and makes no use of smoothing or proximal operators. Apart from these theoretical results, we show experimentally that the algorithm is very practical and in some cases also offers significant computational advantages on large problem instances. We provide an open source implementation that can be adapted for other problems that fit the overall structure.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2075698219</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2075698219</sourcerecordid><originalsourceid>FETCH-proquest_journals_20756982193</originalsourceid><addsrcrecordid>eNqNissKgkAUQIcgSMp_uNBaGMd8LcXSVq2CliJxzTGdW3NH-v1c9AFtzlmcsxKeiqIwyA5KbYTPPEgpVZKqOI48URdwRId20kaz03e4kOGJyPVQ2dY84UZjh1CMD7La9RN8FkJJFhkd1HO7TA6Rd2LdtSOj__NW7KvTtTwHL0vvGdk1A83WLKlRMo2TPFNhHv13fQH9KTu-</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2075698219</pqid></control><display><type>article</type><title>A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees</title><source>ProQuest - Publicly Available Content Database</source><creator>Ravi, Sathya N ; Collins, Maxwell D ; Singh, Vikas</creator><creatorcontrib>Ravi, Sathya N ; Collins, Maxwell D ; Singh, Vikas</creatorcontrib><description>We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the scheme yields so-called coreset results for various Machine Learning problems including 1-median, Balanced Development, Sparse PCA, Graph Cuts, and the \(\ell_1\)-norm-regularized Support Vector Machine (SVM) among others. This means that the algorithm provides approximate solutions to these problems in time complexity bounds that are not dependent on the size of the input problem. Our framework, motivated by a growing body of work on sublinear algorithms for various data analysis problems, is entirely deterministic and makes no use of smoothing or proximal operators. Apart from these theoretical results, we show experimentally that the algorithm is very practical and in some cases also offers significant computational advantages on large problem instances. We provide an open source implementation that can be adapted for other problems that fit the overall structure.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Data analysis ; Machine learning ; Support vector machines</subject><ispartof>arXiv.org, 2017-08</ispartof><rights>2017. 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/2075698219?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25751,37010,44588</link.rule.ids></links><search><creatorcontrib>Ravi, Sathya N</creatorcontrib><creatorcontrib>Collins, Maxwell D</creatorcontrib><creatorcontrib>Singh, Vikas</creatorcontrib><title>A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees</title><title>arXiv.org</title><description>We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the scheme yields so-called coreset results for various Machine Learning problems including 1-median, Balanced Development, Sparse PCA, Graph Cuts, and the \(\ell_1\)-norm-regularized Support Vector Machine (SVM) among others. This means that the algorithm provides approximate solutions to these problems in time complexity bounds that are not dependent on the size of the input problem. Our framework, motivated by a growing body of work on sublinear algorithms for various data analysis problems, is entirely deterministic and makes no use of smoothing or proximal operators. Apart from these theoretical results, we show experimentally that the algorithm is very practical and in some cases also offers significant computational advantages on large problem instances. We provide an open source implementation that can be adapted for other problems that fit the overall structure.</description><subject>Algorithms</subject><subject>Data analysis</subject><subject>Machine learning</subject><subject>Support vector machines</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNissKgkAUQIcgSMp_uNBaGMd8LcXSVq2CliJxzTGdW3NH-v1c9AFtzlmcsxKeiqIwyA5KbYTPPEgpVZKqOI48URdwRId20kaz03e4kOGJyPVQ2dY84UZjh1CMD7La9RN8FkJJFhkd1HO7TA6Rd2LdtSOj__NW7KvTtTwHL0vvGdk1A83WLKlRMo2TPFNhHv13fQH9KTu-</recordid><startdate>20170822</startdate><enddate>20170822</enddate><creator>Ravi, Sathya N</creator><creator>Collins, Maxwell D</creator><creator>Singh, Vikas</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>20170822</creationdate><title>A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees</title><author>Ravi, Sathya N ; Collins, Maxwell D ; Singh, Vikas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20756982193</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Data analysis</topic><topic>Machine learning</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>Ravi, Sathya N</creatorcontrib><creatorcontrib>Collins, Maxwell D</creatorcontrib><creatorcontrib>Singh, Vikas</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 Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>ProQuest - 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>Ravi, Sathya N</au><au>Collins, Maxwell D</au><au>Singh, Vikas</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees</atitle><jtitle>arXiv.org</jtitle><date>2017-08-22</date><risdate>2017</risdate><eissn>2331-8422</eissn><abstract>We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the scheme yields so-called coreset results for various Machine Learning problems including 1-median, Balanced Development, Sparse PCA, Graph Cuts, and the \(\ell_1\)-norm-regularized Support Vector Machine (SVM) among others. This means that the algorithm provides approximate solutions to these problems in time complexity bounds that are not dependent on the size of the input problem. Our framework, motivated by a growing body of work on sublinear algorithms for various data analysis problems, is entirely deterministic and makes no use of smoothing or proximal operators. Apart from these theoretical results, we show experimentally that the algorithm is very practical and in some cases also offers significant computational advantages on large problem instances. We provide an open source implementation that can be adapted for other problems that fit the overall structure.</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, 2017-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2075698219
source ProQuest - Publicly Available Content Database
subjects Algorithms
Data analysis
Machine learning
Support vector machines
title A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T13%3A15%3A39IST&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%20Deterministic%20Nonsmooth%20Frank%20Wolfe%20Algorithm%20with%20Coreset%20Guarantees&rft.jtitle=arXiv.org&rft.au=Ravi,%20Sathya%20N&rft.date=2017-08-22&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2075698219%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20756982193%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2075698219&rft_id=info:pmid/&rfr_iscdi=true