<?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>2026-11-22T15:12:54Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/7925" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/7925</identifier><datestamp>2017-03-21T20:52:57Z</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="f488261c-eb62-4c7c-8960-4459935de09d" confidence="600">Urner, Ruth</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2013-09-26T17:29:15Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2013-09-26T17:29:15Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2013-09-26T17:29:15Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2013</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/7925</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Machine learning has enjoyed astounding practical&#xd;
success in a wide range of applications in recent&#xd;
years-practical success that often hurries ahead of our&#xd;
theoretical understanding. The standard framework for machine&#xd;
learning theory assumes full supervision, that is, training data&#xd;
consists of correctly labeled iid examples from the same task&#xd;
that the learned classifier is supposed to be applied to.&#xd;
However, many practical applications successfully make use of&#xd;
the sheer abundance of data that is currently produced. Such&#xd;
data may not be labeled or may be collected from various&#xd;
sources.&#xd;
&#xd;
The focus of this thesis is to provide theoretical analysis of&#xd;
machine learning regimes where the learner is given such&#xd;
(possibly large amounts) of non-perfect training data. In&#xd;
particular, we investigate the benefits and limitations of&#xd;
learning with unlabeled data in semi-supervised learning and&#xd;
active learning as well as benefits and limitations of learning&#xd;
from data that has been generated by a task that is different&#xd;
from the target task (domain adaptation learning).&#xd;
For all three settings, we propose&#xd;
Probabilistic Lipschitzness to model the relatedness between the labels and the underlying domain space, and we&#xd;
discuss our suggested notion by comparing it to other common&#xd;
data assumptions.</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 theory</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">Sample complexity</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">Unlabeled data</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="program" lang="en">Computer Science</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Learning with non-Standard Supervision</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="comment" qualifier="hidden" lang="en">The work of my thesis is based on five publications. I have verified for each that the publishers expressly allow (this is stated in the copyright/publication forms that I signed) to use the published material in my doctoral dissertation.</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>