<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.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>2026-11-21T01:10:25Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/30992" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/30992</identifier><datestamp>2026-09-24T22:07:10Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</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="advisor">Kratsios, Anastasis</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Hong, Ruiyang</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Mathematics and Statistics</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2025-01-29T20:11:00Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2025-01-29T20:11:00Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2024</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/30992</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/21101</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that generalize but may be too small/constrained to be universal approximators. Motivated by real−world deep learning implementations that are both expressive and statistically reliable, we ask: "Is there a class of neural networks that is both large enough to be universal but structured enough to generalize?" This paper constructively provides a positive answer to this question by identifying a highly structured class of ReLU multilayer perceptions (MLPs), which are optimal function approximators and are statistically well−behaved. We show that any L−Lipschitz function from [0,1]ᵈ to [−n,n] can be approximated to a uniform Ld/(2n) error on [0,1]ᵈ with a sparsely connected L−Lipschitz ReLU MLP of width 𝒪(dnᵈ), depth 𝒪(łog(d)), with 𝒪(dnᵈ) nonzero parameters, and whose weights and biases take values in {0,± 1/2} except in the first and last layers which instead have magnitude at−most $n$. Unlike previously known "large" classes of universal ReLU MLPs, the empirical Rademacher complexity of our class remains bounded even when its depth and width become arbitrarily large.&#xd;
&#xd;
Further, our class of MLPs achieves a near−optimal sample complexity of 𝒪(łog(N)/√{N}) when given N i.i.d. normalized sub−Gaussian training samples. We achieve this by avoiding the standard approach to constructing optimal ReLU approximators, which sacrifices regularity by relying on small spikes. Instead, we introduce a new construction that perfectly fits together linear pieces using Kuhn triangulations and avoids these small spikes.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Master of Science (MSc)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Lipschitz Neural Networks</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Optimal Approximation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Generalization Bounds</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Optimal Interpolation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Optimal Lipschitz Constant</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Kuhn Triangulation</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Universal Approximation</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>