<?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>2026-11-21T05:01:45Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/28364" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/28364</identifier><datestamp>2026-09-24T21:01:43Z</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">Arbas, Jamil</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Computer Science</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2023-03-17T20:02:21Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2023-03-17T20:02:21Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2023</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/28364</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/18106</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">We develop a technique for privately estimating the parameters of a mixture distribution&#xd;
by reducing the problem to its non-private counterpart. This technique allows us&#xd;
to privatize existing non-private algorithms in a BlackBox manner while only incurring&#xd;
a small overhead in sample complexity and running time.&#xd;
As the main application of our framework, we develop an algorithm for privately&#xd;
learning mixtures of Gaussians using the non-private algorithm of Moitra and Valiant&#xd;
[MV10] as a BlackBox and incurs only a polynomial time overhead in the sample complexity&#xd;
and computational complexity. As a result, this gives the first sample complexity&#xd;
upper bound and the first polynomial time algorithm in d for learning the parameters of&#xd;
the Gaussian Mixture Models privately without requiring any boundedness assumptions&#xd;
on the parameters.&#xd;
To prove the results we introduced Private Populous Estimator (PPE) which is a&#xd;
generalized version of the one used in [AL22] to achieve (ϵ, δ)-differential privacy. We&#xd;
also develop a new masking mechanism for a single Gaussian component. Then we&#xd;
introduce a general recipe to turn a masking mechanism for a component into a masking&#xd;
mechanism for mixtures.</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">Differential Privacy</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Gaussian Mixture Models</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Polynomial time and private learning of unbounded 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>