<?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>2026-11-21T04:31:08Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/26804" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/26804</identifier><datestamp>2026-09-24T22:23:18Z</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">Aden-Ali, Ishaq</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">2021-08-23T19:58:45Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2021-08-23T19:58:45Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2021</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/26804</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/24673</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Multivariate Gaussians: We provide sample complexity upper bounds for semi-agnostically&#xd;
learning multivariate Gaussians under the constraint of approximate differential&#xd;
privacy. These are the first  finite sample upper bounds for general Gaussians&#xd;
which do not impose restrictions on the parameters of the distribution. Our bounds&#xd;
are near-optimal in the case when the covariance is known to be the identity, and&#xd;
conjectured to be near-optimal in the general case. From a technical standpoint, we&#xd;
provide analytic tools for arguing the existence of global "locally small" covers from&#xd;
local covers of the space. These are exploited using modifications of recent techniques&#xd;
for for differentially private hypothesis selection.&#xd;
Mixtures of Gaussians: We consider the problem of learning mixtures of Gaussians&#xd;
under the constraint of approximate differential privacy. We provide the first&#xd;
sample complexity upper bounds for privately learning mixtures of unbounded axis-aligned&#xd;
(or even unbounded univariate) Gaussians. To prove our results, we design&#xd;
a new technique for privately learning mixture distributions. A class of distributions&#xd;
F is said to be list-decodable if there is an algorithm that, given "heavily corrupted"&#xd;
samples from a distribution f in F, outputs a list of distributions, H, such that one of the distributions in H approximates f. We show that if F is privately list-decodable then&#xd;
we can privately learn mixtures of distributions in F. Finally, we show axis-aligned&#xd;
Gaussian distributions are privately list-decodable, thereby proving mixtures of such&#xd;
distributions are privately learnable.</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">Is it possible to estimate an unknown probability distribution given random samples from it? This is a fundamental problem known as distribution learning (or density estimation) that has been studied by statisticians for decades, and in recent years has become a topic of interest for computer scientists. While distribution learning is a mature and well understood problem, in many cases the samples (or data) we observe may consist of sensitive information belonging to individuals and well-known solutions may inadvertently result in the leakage of private information. &#xd;
In this thesis we study distribution learning under the assumption that the data is generated from high-dimensional Gaussians (or their mixtures) with the aim of understanding how many samples an algorithm needs before it can guarantee a good estimate. Furthermore, to protect against leakage of private information, we consider approaches that satisfy differential privacy — the gold standard for modern private data analysis.</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">PAC learning, Learning Theory, Distribution Learning, Differential Privacy, Mixtures of Gaussians</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">On the Sample Complexity of Privately Learning Gaussians and their Mixtures</dim:field>
   <dim:field mdschema="dc" element="title" qualifier="alternative" lang="en_US">Privately Learning Gaussians and their Mixtures</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>