{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/113119"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/113119","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Understanding generalization","abstract":"An important goal in machine learning is to understand how to design models that can generalize. This thesis follows a venerable line of research aimed at understanding generalization through the lens of stability- the study of how variations on the inputs of a system can cause its outputs to change. We explore stability and generalization in two different directions. In the first direction we look at proving stability using a proof technique provided by Hardt et al [HRS16]. We apply this technique to stochastic gradient descent with momentum and investigate the resulting stability bounds under some assumptions. In the second direction, we explore the effectiveness of stability in obtaining generalization bounds under the violation of some model assumptions. In particular, we show that stability is insufficient for generalization under domain adaptation. We introduce a sufficient condition and show that some properties can imply this condition.","abstract_html":"An important goal in machine learning is to understand how to design models that can generalize. This thesis follows a venerable line of research aimed at understanding generalization through the lens of stability- the study of how variations on the inputs of a system can cause its outputs to change. We explore stability and generalization in two different directions. In the first direction we look at proving stability using a proof technique provided by Hardt et al [HRS16]. We apply this technique to stochastic gradient descent with momentum and investigate the resulting stability bounds under some assumptions. In the second direction, we explore the effectiveness of stability in obtaining generalization bounds under the violation of some model assumptions. In particular, we show that stability is insufficient for generalization under domain adaptation. We introduce a sufficient condition and show that some properties can imply this condition.","abstract_has_math":false,"creators":["Ong, Ming Yang"],"institution":"Massachusetts Institute of Technology","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.","school":null,"contributors":[],"advisors":["Pablo A. Parrilo."],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017","date_published":"2017","updated_at":"2026-07-22T22:20:48Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1721.1/113119","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Pablo A. Parrilo."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Ong, Ming Yang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2018-01-12T20:57:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2018-01-12T20:57:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2017"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1721.1/113119"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.","This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 61-62)."]},{"key":"dc:description.abstract","label":"Abstract","values":["An important goal in machine learning is to understand how to design models that can generalize. This thesis follows a venerable line of research aimed at understanding generalization through the lens of stability- the study of how variations on the inputs of a system can cause its outputs to change. We explore stability and generalization in two different directions. In the first direction we look at proving stability using a proof technique provided by Hardt et al [HRS16]. We apply this technique to stochastic gradient descent with momentum and investigate the resulting stability bounds under some assumptions. In the second direction, we explore the effectiveness of stability in obtaining generalization bounds under the violation of some model assumptions. In particular, we show that stability is insufficient for generalization under domain adaptation. We introduce a sufficient condition and show that some properties can imply this condition."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M. Eng."]},{"key":"dc:title","label":"Title","values":["Understanding generalization"]}]}],"canonical_facts":{"dc:contributor.advisor":["Pablo A. Parrilo."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Ong, Ming Yang"],"dc:date.accessioned":["2018-01-12T20:57:17Z"],"dc:date.available":["2018-01-12T20:57:17Z"],"dc:date.issued":["2017"],"dc:description":["Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.","This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 61-62)."],"dc:description.abstract":["An important goal in machine learning is to understand how to design models that can generalize. This thesis follows a venerable line of research aimed at understanding generalization through the lens of stability- the study of how variations on the inputs of a system can cause its outputs to change. We explore stability and generalization in two different directions. In the first direction we look at proving stability using a proof technique provided by Hardt et al [HRS16]. We apply this technique to stochastic gradient descent with momentum and investigate the resulting stability bounds under some assumptions. In the second direction, we explore the effectiveness of stability in obtaining generalization bounds under the violation of some model assumptions. In particular, we show that stability is insufficient for generalization under domain adaptation. We introduce a sufficient condition and show that some properties can imply this condition."],"dc:description.degree":["M. Eng."],"dc:identifier.uri":["http://hdl.handle.net/1721.1/113119"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Understanding generalization"],"dc:type":["Thesis"]},"updated_at":"2026-07-22T22:20:48Z"}