<?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>2026-11-22T04:15:14Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/4445" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/4445</identifier><datestamp>2017-03-21T18:19:36Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9930</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="06bd0132-c3c8-449e-8b89-612aec07e84d" confidence="600">Pal, David</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2009-05-22T14:03:10Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2009-05-22T14:03:10Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2009-05-22T14:03:10Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2009-05-21</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/4445</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">This thesis studies two problems in theoretical machine learning. The first&#xd;
part of the thesis investigates the statistical stability of clustering&#xd;
algorithms.  In the second part, we study the relative advantage of having&#xd;
unlabeled data in classification problems.&#xd;
&#xd;
Clustering stability was proposed and used as a model selection method in&#xd;
clustering tasks. The main idea of the method is that from a given data set&#xd;
two independent samples are taken. Each sample individually is clustered with&#xd;
the same clustering algorithm, with the same setting of its parameters.  If the&#xd;
two resulting clusterings turn out to be close in some metric, it is concluded&#xd;
that the clustering algorithm and the setting of its parameters match the data&#xd;
set, and that clusterings obtained are meaningful. We study asymptotic&#xd;
properties of this method for certain types of cost minimizing clustering&#xd;
algorithms and relate their asymptotic stability to the number of optimal&#xd;
solutions of the underlying optimization problem.&#xd;
&#xd;
In classification problems, it is often expensive to obtain labeled data, but&#xd;
on the other hand, unlabeled data are often plentiful and cheap. We study how&#xd;
the access to unlabeled data can decrease the amount of labeled data&#xd;
needed in the worst-case sense. We propose an extension of the probably&#xd;
approximately correct (PAC) model in which this question can be naturally&#xd;
studied.  We show that for certain basic tasks the access to unlabeled data&#xd;
might, at best, halve the amount of labeled data needed.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">machine learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">statistics</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">unsupervised learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">semi-supervised learning</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">learning theory</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="program" lang="en">Computer Science</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Contributions to Unsupervised and Semi-Supervised Learning</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending" lang="en">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>