<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T10:00:08Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/120780" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/120780</identifier><datestamp>2026-05-15T17:52:55Z</datestamp><setSpec>com_1813_35</setSpec><setSpec>col_1813_47</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Rioux, Gabriel</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair" lang="en_US">Goldfeld, Ziv</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Kato, Kengo</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Yang, Yunan</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-04-02T18:49:36Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2026-04-02T18:49:36Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025-08</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Submission ID: 15086</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">ProQuest Publication ID: 32121277</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/120780</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/wesk-vd20</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="bibid">17422435</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">314 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Over the past two decades, the statistical and computational properties of optimal transport (OT) have been systematically studied, driven in part by OT's broad applicability across data science, statistics, economics, physics, and other fields. This body of work has identified the curse of dimensionality inherent in statistical estimation with OT distances  and has led the development of computationally and statistically efficient regularizations of OT. The first contribution of this thesis is a general framework for deriving limit distributions and other asymptotic properties of empirical regularized OT distances. While OT distances enable a natural comparison between distributions on a common space, comparing datasets of different types -- such as text and images -- requires specifying an ad hoc cost function, which may fail to capture a meaningful correspondence between data points. To address this issue, Gromov-Wasserstein (GW) distances have been proposed, enabling  a comparison of metric measure spaces based on their intrinsic structure. As a result, GW distances have  found widespread use in applications involving heterogeneous data. The second contribution of this thesis is to establish the first limit laws for empirical GW distances and to derive consistent resampling schemes. Given the broad applicability of GW distances, their computation is of a particular interest. However, existing algorithms for computing regularized GW distances lack comprehensive convergence rate guarantees. To address this gap, the final contribution of this thesis is to introduce the first algorithms for computing regularized GW distances subject to formal non-asymptotic convergence rate guarantees.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights">Attribution 4.0 International</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">https://creativecommons.org/licenses/by/4.0/</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Continuous optimization</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Gromov-Wasserstein distances</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Limit theorems</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Nonsmooth analysis</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Optimal transport</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Regularization</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Computational and Statistical Properties of Optimal Transport-Based Distances</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">dissertation or thesis</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="discipline">Applied Mathematics</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="grantor">Cornell University</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="level">Doctor of Philosophy</dim:field>
   <dim:field mdschema="thesis" element="degree" qualifier="name">Ph. D., Applied Mathematics</dim:field>
   <dim:field mdschema="dcterms" element="license">https://hdl.handle.net/1813/59810.2</dim:field>
   <dim:field mdschema="dspace" element="entity" qualifier="type">Publication</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="collection" authority="https://ecommons.cornell.edu/handle/1813/47" confidence="600">Cornell Theses and Dissertations</dim:field>
   <dim:field mdschema="cris" element="virtual" qualifier="author">Rioux, Gabriel</dim:field>
   <dim:field mdschema="cris" element="virtualsource" qualifier="collection">5893a6ea-7af3-41d7-abc6-04bcd26ab5df</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
   <dim:field mdschema="cerif" element="openaire" authority="" confidence="-1">&lt;Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="5572c560-9574-45fe-81a7-9696eb012dcb">
	&lt;Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843&lt;/Type>
	&lt;Language>en&lt;/Language>
   	&lt;Title>Computational and Statistical Properties of Optimal Transport-Based Distances&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2025-08&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/wesk-vd20&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Rioux, Gabriel&lt;/DisplayName>
         	&lt;Affiliation>
         		&lt;OrgUnit>
         		&lt;/OrgUnit>
         	&lt;/Affiliation>
      	&lt;/Author>
	&lt;/Authors>
   	&lt;Editors>
	&lt;/Editors>
    &lt;Publishers>
        &lt;Publisher>
            &lt;OrgUnit />
        &lt;/Publisher>
    &lt;/Publishers>
    &lt;License>https://creativecommons.org/licenses/by/4.0/&lt;/License>
    &lt;Keyword>Continuous optimization&lt;/Keyword>
    &lt;Keyword>Gromov-Wasserstein distances&lt;/Keyword>
    &lt;Keyword>Limit theorems&lt;/Keyword>
    &lt;Keyword>Nonsmooth analysis&lt;/Keyword>
    &lt;Keyword>Optimal transport&lt;/Keyword>
    &lt;Keyword>Regularization&lt;/Keyword>
   	&lt;Abstract>Over the past two decades, the statistical and computational properties of optimal transport (OT) have been systematically studied, driven in part by OT&amp;apos;s broad applicability across data science, statistics, economics, physics, and other fields. This body of work has identified the curse of dimensionality inherent in statistical estimation with OT distances  and has led the development of computationally and statistically efficient regularizations of OT. The first contribution of this thesis is a general framework for deriving limit distributions and other asymptotic properties of empirical regularized OT distances. While OT distances enable a natural comparison between distributions on a common space, comparing datasets of different types -- such as text and images -- requires specifying an ad hoc cost function, which may fail to capture a meaningful correspondence between data points. To address this issue, Gromov-Wasserstein (GW) distances have been proposed, enabling  a comparison of metric measure spaces based on their intrinsic structure. As a result, GW distances have  found widespread use in applications involving heterogeneous data. The second contribution of this thesis is to establish the first limit laws for empirical GW distances and to derive consistent resampling schemes. Given the broad applicability of GW distances, their computation is of a particular interest. However, existing algorithms for computing regularized GW distances lack comprehensive convergence rate guarantees. To address this gap, the final contribution of this thesis is to introduce the first algorithms for computing regularized GW distances subject to formal non-asymptotic convergence rate guarantees.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>