A Fast Proximal Point Method for Computing Exact Wasserstein Distance
Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we wi...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2019-06 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Xie, Yujia Wang, Xiangfeng Wang, Ruijia Zha, Hongyuan |
description | Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when apply to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2073907793</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2073907793</sourcerecordid><originalsourceid>FETCH-proquest_journals_20739077933</originalsourceid><addsrcrecordid>eNqNykELgjAYgOERBEn5Hz7oLKwtWx7DlC6Bh6CjDJs10c32fYI_vw79gE7v4XkXLBJS7pLjXogVixE7zrk4KJGmMmLFCUqNBFXwsx10D5W3juBq6OUf0PoAuR_Giax7QjHrhuCuEU1AMtbB2SJp15gNW7a6RxP_umbbsrjll2QM_j0ZpLrzU3BfqgVXMuNKZVL-d30AMD86gw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2073907793</pqid></control><display><type>article</type><title>A Fast Proximal Point Method for Computing Exact Wasserstein Distance</title><source>Freely Accessible Journals</source><creator>Xie, Yujia ; Wang, Xiangfeng ; Wang, Ruijia ; Zha, Hongyuan</creator><creatorcontrib>Xie, Yujia ; Wang, Xiangfeng ; Wang, Ruijia ; Zha, Hongyuan</creatorcontrib><description>Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when apply to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Artificial intelligence ; Center of gravity ; Computation ; Image processing ; Iterative methods ; Machine learning ; Mathematical models ; Numerical stability ; Parameters ; Performance degradation ; Regularization</subject><ispartof>arXiv.org, 2019-06</ispartof><rights>2019. 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><link.rule.ids>781,785</link.rule.ids></links><search><creatorcontrib>Xie, Yujia</creatorcontrib><creatorcontrib>Wang, Xiangfeng</creatorcontrib><creatorcontrib>Wang, Ruijia</creatorcontrib><creatorcontrib>Zha, Hongyuan</creatorcontrib><title>A Fast Proximal Point Method for Computing Exact Wasserstein Distance</title><title>arXiv.org</title><description>Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when apply to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter.</description><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Center of gravity</subject><subject>Computation</subject><subject>Image processing</subject><subject>Iterative methods</subject><subject>Machine learning</subject><subject>Mathematical models</subject><subject>Numerical stability</subject><subject>Parameters</subject><subject>Performance degradation</subject><subject>Regularization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNykELgjAYgOERBEn5Hz7oLKwtWx7DlC6Bh6CjDJs10c32fYI_vw79gE7v4XkXLBJS7pLjXogVixE7zrk4KJGmMmLFCUqNBFXwsx10D5W3juBq6OUf0PoAuR_Giax7QjHrhuCuEU1AMtbB2SJp15gNW7a6RxP_umbbsrjll2QM_j0ZpLrzU3BfqgVXMuNKZVL-d30AMD86gw</recordid><startdate>20190624</startdate><enddate>20190624</enddate><creator>Xie, Yujia</creator><creator>Wang, Xiangfeng</creator><creator>Wang, Ruijia</creator><creator>Zha, Hongyuan</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>20190624</creationdate><title>A Fast Proximal Point Method for Computing Exact Wasserstein Distance</title><author>Xie, Yujia ; Wang, Xiangfeng ; Wang, Ruijia ; Zha, Hongyuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20739077933</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Center of gravity</topic><topic>Computation</topic><topic>Image processing</topic><topic>Iterative methods</topic><topic>Machine learning</topic><topic>Mathematical models</topic><topic>Numerical stability</topic><topic>Parameters</topic><topic>Performance degradation</topic><topic>Regularization</topic><toplevel>online_resources</toplevel><creatorcontrib>Xie, Yujia</creatorcontrib><creatorcontrib>Wang, Xiangfeng</creatorcontrib><creatorcontrib>Wang, Ruijia</creatorcontrib><creatorcontrib>Zha, Hongyuan</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>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>Access via ProQuest (Open Access)</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>Xie, Yujia</au><au>Wang, Xiangfeng</au><au>Wang, Ruijia</au><au>Zha, Hongyuan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Fast Proximal Point Method for Computing Exact Wasserstein Distance</atitle><jtitle>arXiv.org</jtitle><date>2019-06-24</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when apply to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter.</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, 2019-06 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2073907793 |
source | Freely Accessible Journals |
subjects | Algorithms Artificial intelligence Center of gravity Computation Image processing Iterative methods Machine learning Mathematical models Numerical stability Parameters Performance degradation Regularization |
title | A Fast Proximal Point Method for Computing Exact Wasserstein Distance |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T06%3A05%3A03IST&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%20Fast%20Proximal%20Point%20Method%20for%20Computing%20Exact%20Wasserstein%20Distance&rft.jtitle=arXiv.org&rft.au=Xie,%20Yujia&rft.date=2019-06-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2073907793%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2073907793&rft_id=info:pmid/&rfr_iscdi=true |