<?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>2026-11-21T04:25:07Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/29765" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/29765</identifier><datestamp>2026-09-24T05:11:56Z</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">Ashtiani, Hassan</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Afzali Kharkouei, Mohammad</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Computing and Software</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2024-05-07T19:52:44Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2024-05-07T19:52:44Z</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/11375/29765</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/18192</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">We develop a general technique for estimating (mixture) distributions under the constraint&#xd;
of differential privacy (DP). On a high level, we show that if a class of distributions&#xd;
(such as Gaussians) is (1) list decodable and (2) admits a “locally small”&#xd;
cover (Bun et al., 2021) with respect to total variation distance, then the class of its&#xd;
mixtures is privately learnable. The proof circumvents a known barrier indicating&#xd;
that, unlike Gaussians, GMMs do not admit a locally small cover (Aden-Ali et al.,&#xd;
2021b).&#xd;
As the main application, we study the problem of privately estimating mixtures of&#xd;
Gaussians. Our main result is that poly(k, d, 1/α, 1/ε, log(1/δ)) samples are sufficient&#xd;
to estimate a mixture of k Gaussians in R^d up to total variation distance ``α'' while&#xd;
satisfying (ε, δ)-DP. This is the first finite sample complexity upper bound for the&#xd;
problem that does not make any structural assumptions on the GMMs.</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="description" qualifier="layabstract" lang="en_US">The problem of distribution learning, also known as density estimation, has been extensively&#xd;
explored in Statistics over several decades. It involves the task of recovering&#xd;
the original distribution with minimal error given a set of samples from a distribution&#xd;
that belongs to a known family of distributions.&#xd;
More recently, a branch of research has emerged focusing on private distribution&#xd;
learning. This approach aims to learn a class of distributions while safeguarding the&#xd;
privacy of individuals in the dataset through the fulfillment of the gold standard of&#xd;
differential privacy. A fundamental open question in this domain is: Is there a class of&#xd;
distributions that can be learned without privacy considerations but not with privacy&#xd;
preservation?&#xd;
To address this question, we delve into the private learnability of the class of&#xd;
mixtures of Gaussians, which represents a diverse and complex set of distributions.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en_US</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Distribution Learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Differential Privacy</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Gaussian Mixture Models</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Density Estimation</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">PRIVATE DENSITY ESTIMATION FOR MIXTURE DISTRIBUTIONS AND GAUSSIAN MIXTURE MODELS</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>