<?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>2026-11-22T10:35:18Z</responseDate><request verb="GetRecord" identifier="oai:ecommons.cornell.edu:1813/126569" metadataPrefix="dim">https://ecommons.cornell.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:ecommons.cornell.edu:1813/126569</identifier><datestamp>2026-08-27T03:18:43Z</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">Yu, Annan</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="chair" lang="en_US">Townsend, Alex</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Damle, Anil</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="committeeMember" lang="en_US">Dean, Sarah</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-08-26T19:51:16Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2026-08-26T19:51:16Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026-05</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">Yu_cornellgrad_0058F_15458</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">https://www.proquest.com/LegacyDocView/DISSNUM/32449858</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1813/126569</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="doi">https://doi.org/10.7298/b5d4-7x48</dim:field>
   <dim:field mdschema="dc" element="description" lang="en_US">277 pages</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Artificial intelligence has advanced rapidly in recent years, driven largely by the success of neural networks trained at unprecedented scale.A defining feature of these models is their scalability: as model size, data, and compute increase, performance often improves in a predictable manner, enabling the solution of increasingly complex problems. Despite this success, fundamental questions remain. Neural networks are typically highly overparameterized and trained on noisy, finite datasets, yet they often generalize well without explicit regularization. Understanding why this is possible remains a central challenge in modern machine learning. Two closely related concepts play a key role in addressing this challenge: implicit regularization and inductive bias. Implicit regularization refers to the tendency of the training process itself --- through optimization algorithms, parameterization, and initialization --- to favor certain solutions over others, even in the absence of explicit regularization terms. Inductive biases describe the structural preferences encoded by a model’s architecture and design choices, which guide learning toward solutions that generalize beyond the training data. This dissertation focuses on understanding these two aspects of neural network training.We study the implicit regularization and inductive biases of several widely used model classes, including multi-layer perceptrons, state-space models, and Transformer architectures. Across these settings, we analyze how frequency structure, rank structure, and long-range dependencies emerge during training, and how they are shaped by architectural choices and parameterization. Importantly, we go beyond characterization and show how these effects can be tuned in a principled way through data design, model construction, and training procedures. By clarifying how implicit regularization and inductive biases arise and evolve, this work provides a unified perspective on the generalization behavior of modern neural networks and offers practical guidance for designing scalable models that are better aligned with the structure of the tasks they are intended to solve.</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">Fourier Analysis</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Machine Learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Neural Networks</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">State Space Models</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Time Series</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Transformers</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Implicit Regularization and Inductive Biases in Neural Network Training</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">Yu, Annan</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="7177cb46-7256-4463-9310-baf0a76e5b32">
	&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>Implicit Regularization and Inductive Biases in Neural Network Training&lt;/Title>
   	&lt;PublishedIn>
    	&lt;Publication>
      	&lt;/Publication>
   	&lt;/PublishedIn>
   	&lt;PublicationDate>2026-05&lt;/PublicationDate>
   	&lt;DOI>https://doi.org/10.7298/b5d4-7x48&lt;/DOI>
   	&lt;Authors>
      	&lt;Author>
        	&lt;DisplayName>Yu, Annan&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>Fourier Analysis&lt;/Keyword>
    &lt;Keyword>Machine Learning&lt;/Keyword>
    &lt;Keyword>Neural Networks&lt;/Keyword>
    &lt;Keyword>State Space Models&lt;/Keyword>
    &lt;Keyword>Time Series&lt;/Keyword>
    &lt;Keyword>Transformers&lt;/Keyword>
   	&lt;Abstract>Artificial intelligence has advanced rapidly in recent years, driven largely by the success of neural networks trained at unprecedented scale.A defining feature of these models is their scalability: as model size, data, and compute increase, performance often improves in a predictable manner, enabling the solution of increasingly complex problems. Despite this success, fundamental questions remain. Neural networks are typically highly overparameterized and trained on noisy, finite datasets, yet they often generalize well without explicit regularization. Understanding why this is possible remains a central challenge in modern machine learning. Two closely related concepts play a key role in addressing this challenge: implicit regularization and inductive bias. Implicit regularization refers to the tendency of the training process itself --- through optimization algorithms, parameterization, and initialization --- to favor certain solutions over others, even in the absence of explicit regularization terms. Inductive biases describe the structural preferences encoded by a model’s architecture and design choices, which guide learning toward solutions that generalize beyond the training data. This dissertation focuses on understanding these two aspects of neural network training.We study the implicit regularization and inductive biases of several widely used model classes, including multi-layer perceptrons, state-space models, and Transformer architectures. Across these settings, we analyze how frequency structure, rank structure, and long-range dependencies emerge during training, and how they are shaped by architectural choices and parameterization. Importantly, we go beyond characterization and show how these effects can be tuned in a principled way through data design, model construction, and training procedures. By clarifying how implicit regularization and inductive biases arise and evolve, this work provides a unified perspective on the generalization behavior of modern neural networks and offers practical guidance for designing scalable models that are better aligned with the structure of the tasks they are intended to solve.&lt;/Abstract>
	&lt;Access xmlns="http://purl.org/coar/access_right" 
    >
    &lt;/Access>
&lt;/Publication>
</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>