<?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>2026-11-21T02:18:37Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/33442" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/33442</identifier><datestamp>2026-08-08T07:09:34Z</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">Ayers, Paul</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Chuiko, Valerii</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department">Chemistry</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-08-07T13:52:18Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/11375/33442</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/2226</dim:field>
   <dim:field mdschema="dc" element="description">Traditional quantum chemistry methods face fundamental limitations: wavefunction theory suffers from the curse of dimensionality, while the exact density functional remains unknown. While reduced density matrix functional theory (RDMFT) offers a mathematically compact alternative, it is still bound by the trade-off between computational cost and accuracy. Recent advances in machine- and deep-learning attempt to bridge this gap, yet prevailing graph-based models often fail to capture essential physical invariances or achieve the accuracy of standard ab initio methods.

This thesis overcomes these limitations by integrating compact quantum mechanical representations with specialized deep learning architectures. We first explore a highly condensed wavefunction formulation based on the statistical analysis of electron populations. We then introduce a novel, fully invariant electronic descriptor. Coupled with a set transformer architecture, this descriptor predicts the energies of strongly-correlated molecular systems with chemical accuracy. Finally, we generalize this descriptor to predict the full one- and two-electron reduced density matrices. Using an exceptionally lightweight neural network, this proposed methodology outperforms current state-of-the-art deep learning models, establishing a highly efficient, physically rigorous framework for electronic structure prediction.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">quantum chemistry, machine learning, deep learning, set transformer, electronic descriptor, reduced density matrix, electron correlation, N-representability</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights" lang="en">Attribution-NonCommercial 2.5 Canada</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">http://creativecommons.org/licenses/by-nc/2.5/ca/</dim:field>
   <dim:field mdschema="dc" element="title">Paying attention to long-range electron correlations: A Set Transformer Framework for Fully Invariant Electronic Descriptors</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">embargo</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>