Optimal Transport losses and Sinkhorn algorithm with general convex regularization

We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and propose a generalized Sinkhorn algorithm. Our framework unifies many regularizations and numerical methods previously app...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-07
Main Authors: Simone Di Marino, Gerolin, Augusto
Format: Article
Language:English
Subjects:
Algorithms
Numerical methods
Regularization
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 Simone Di Marino
Gerolin, Augusto
description We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and propose a generalized Sinkhorn algorithm. Our framework unifies many regularizations and numerical methods previously appeared in the literature. We show the existence of the maximizer for the dual problem, complementary slackness conditions, providing a complete characterization of solutions for such class of variational problems. As a consequence, we study structural properties of these losses, including continuity, differentiability and provide explicit formulas for the its gradient. Finally, we provide theoretical guarantees of convergences and stability of the generalized Sinkhorn algorithm, even in the continuous setting. The techniques developed here are directly applicable also to study Wasserstein barycenters or, more generally, multi-marginal problems.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2419780734</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2419780734</sourcerecordid><originalsourceid>FETCH-proquest_journals_24197807343</originalsourceid><addsrcrecordid>eNqNi7EKwjAURYMgWLT_EHAupElr6yyKm6DdJWhsU9OX-l6q4tfbwQ9wuWc4505YJJVKkzKTcsZiolYIIVeFzHMVseOhD7bTjleogXqPgTtPZIhruPKThXvjEbh2tUcbmo6_xuW1AYPj6eLhad4cTT04jfajg_WwYNObdmTiH-dsudtWm33So38MhsK59QPCqM4yS9dFKQqVqf-qL4MkQPA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2419780734</pqid></control><display><type>article</type><title>Optimal Transport losses and Sinkhorn algorithm with general convex regularization</title><source>Publicly Available Content (ProQuest)</source><creator>Simone Di Marino ; Gerolin, Augusto</creator><creatorcontrib>Simone Di Marino ; Gerolin, Augusto</creatorcontrib><description>We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and propose a generalized Sinkhorn algorithm. Our framework unifies many regularizations and numerical methods previously appeared in the literature. We show the existence of the maximizer for the dual problem, complementary slackness conditions, providing a complete characterization of solutions for such class of variational problems. As a consequence, we study structural properties of these losses, including continuity, differentiability and provide explicit formulas for the its gradient. Finally, we provide theoretical guarantees of convergences and stability of the generalized Sinkhorn algorithm, even in the continuous setting. The techniques developed here are directly applicable also to study Wasserstein barycenters or, more generally, multi-marginal problems.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Numerical methods ; Regularization</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/2419780734?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25731,36989,44566</link.rule.ids></links><search><creatorcontrib>Simone Di Marino</creatorcontrib><creatorcontrib>Gerolin, Augusto</creatorcontrib><title>Optimal Transport losses and Sinkhorn algorithm with general convex regularization</title><title>arXiv.org</title><description>We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and propose a generalized Sinkhorn algorithm. Our framework unifies many regularizations and numerical methods previously appeared in the literature. We show the existence of the maximizer for the dual problem, complementary slackness conditions, providing a complete characterization of solutions for such class of variational problems. As a consequence, we study structural properties of these losses, including continuity, differentiability and provide explicit formulas for the its gradient. Finally, we provide theoretical guarantees of convergences and stability of the generalized Sinkhorn algorithm, even in the continuous setting. The techniques developed here are directly applicable also to study Wasserstein barycenters or, more generally, multi-marginal problems.</description><subject>Algorithms</subject><subject>Numerical methods</subject><subject>Regularization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNi7EKwjAURYMgWLT_EHAupElr6yyKm6DdJWhsU9OX-l6q4tfbwQ9wuWc4505YJJVKkzKTcsZiolYIIVeFzHMVseOhD7bTjleogXqPgTtPZIhruPKThXvjEbh2tUcbmo6_xuW1AYPj6eLhad4cTT04jfajg_WwYNObdmTiH-dsudtWm33So38MhsK59QPCqM4yS9dFKQqVqf-qL4MkQPA</recordid><startdate>20200702</startdate><enddate>20200702</enddate><creator>Simone Di Marino</creator><creator>Gerolin, Augusto</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>20200702</creationdate><title>Optimal Transport losses and Sinkhorn algorithm with general convex regularization</title><author>Simone Di Marino ; Gerolin, Augusto</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24197807343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Numerical methods</topic><topic>Regularization</topic><toplevel>online_resources</toplevel><creatorcontrib>Simone Di Marino</creatorcontrib><creatorcontrib>Gerolin, Augusto</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 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</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</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>Simone Di Marino</au><au>Gerolin, Augusto</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Optimal Transport losses and Sinkhorn algorithm with general convex regularization</atitle><jtitle>arXiv.org</jtitle><date>2020-07-02</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and propose a generalized Sinkhorn algorithm. Our framework unifies many regularizations and numerical methods previously appeared in the literature. We show the existence of the maximizer for the dual problem, complementary slackness conditions, providing a complete characterization of solutions for such class of variational problems. As a consequence, we study structural properties of these losses, including continuity, differentiability and provide explicit formulas for the its gradient. Finally, we provide theoretical guarantees of convergences and stability of the generalized Sinkhorn algorithm, even in the continuous setting. The techniques developed here are directly applicable also to study Wasserstein barycenters or, more generally, multi-marginal problems.</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_2419780734
source Publicly Available Content (ProQuest)
subjects Algorithms
Numerical methods
Regularization
title Optimal Transport losses and Sinkhorn algorithm with general convex regularization
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T15%3A21%3A46IST&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=Optimal%20Transport%20losses%20and%20Sinkhorn%20algorithm%20with%20general%20convex%20regularization&rft.jtitle=arXiv.org&rft.au=Simone%20Di%20Marino&rft.date=2020-07-02&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2419780734%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_24197807343%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2419780734&rft_id=info:pmid/&rfr_iscdi=true