{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/127008"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/127008","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Representation and transfer learning using information-theoretic approximations","abstract":"Learning informative and transferable feature representations is a key aspect of machine learning systems. Mutual information and Kullback-Leibler divergence are principled and very popular metrics to measure feature relevance and perform distribution matching, respectively. However, clean formulations of machine learning algorithms based on these information-theoretic quantities typically require density estimation, which could be difficult for high dimensional problems. A central theme of this thesis is to translate these formulations into simpler forms that are more amenable to limited data. In particular, we modify local approximations and variational approximations of information-theoretic quantities to propose algorithms for unsupervised and transfer learning. Experiments show that the representations learned by our algorithms perform competitively compared to popular methods that require higher complexity.","abstract_html":"Learning informative and transferable feature representations is a key aspect of machine learning systems. Mutual information and Kullback-Leibler divergence are principled and very popular metrics to measure feature relevance and perform distribution matching, respectively. However, clean formulations of machine learning algorithms based on these information-theoretic quantities typically require density estimation, which could be difficult for high dimensional problems. A central theme of this thesis is to translate these formulations into simpler forms that are more amenable to limited data. In particular, we modify local approximations and variational approximations of information-theoretic quantities to propose algorithms for unsupervised and transfer learning. Experiments show that the representations learned by our algorithms perform competitively compared to popular methods that require higher complexity.","abstract_has_math":false,"creators":["Qiu, David."],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Lizhong Zheng."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-22T22:20:57Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/127008","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lizhong Zheng."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"]},{"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":["Qiu, David."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-09-03T17:41:36Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-09-03T17:41:36Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctoral"]}]},{"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 may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."]},{"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":["https://hdl.handle.net/1721.1/127008"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020","Cataloged from the official PDF of thesis.","Includes bibliographical references (pages 119-127)."]},{"key":"dc:description.abstract","label":"Abstract","values":["Learning informative and transferable feature representations is a key aspect of machine learning systems. Mutual information and Kullback-Leibler divergence are principled and very popular metrics to measure feature relevance and perform distribution matching, respectively. However, clean formulations of machine learning algorithms based on these information-theoretic quantities typically require density estimation, which could be difficult for high dimensional problems. A central theme of this thesis is to translate these formulations into simpler forms that are more amenable to limited data. In particular, we modify local approximations and variational approximations of information-theoretic quantities to propose algorithms for unsupervised and transfer learning. Experiments show that the representations learned by our algorithms perform competitively compared to popular methods that require higher complexity."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph. D."]},{"key":"dc:title","label":"Title","values":["Representation and transfer learning using information-theoretic approximations"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lizhong Zheng."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Qiu, David."],"dc:date.accessioned":["2020-09-03T17:41:36Z"],"dc:date.available":["2020-09-03T17:41:36Z"],"dc:date.issued":["2020"],"dc:description":["Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020","Cataloged from the official PDF of thesis.","Includes bibliographical references (pages 119-127)."],"dc:description.abstract":["Learning informative and transferable feature representations is a key aspect of machine learning systems. Mutual information and Kullback-Leibler divergence are principled and very popular metrics to measure feature relevance and perform distribution matching, respectively. However, clean formulations of machine learning algorithms based on these information-theoretic quantities typically require density estimation, which could be difficult for high dimensional problems. A central theme of this thesis is to translate these formulations into simpler forms that are more amenable to limited data. In particular, we modify local approximations and variational approximations of information-theoretic quantities to propose algorithms for unsupervised and transfer learning. Experiments show that the representations learned by our algorithms perform competitively compared to popular methods that require higher complexity."],"dc:description.degree":["Ph. D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/127008"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Representation and transfer learning using information-theoretic approximations"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral"]},"updated_at":"2026-07-22T22:20:57Z"}