2026-09-19T00:56:56Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1270082026-06-16T18:53:00Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Lizhong Zheng. Qiu, David. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2020-09-03T17:41:36Z 2020-09-03T17:41:36Z 2020 2020 https://hdl.handle.net/1721.1/127008 1191230439 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). 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. by David Qiu. Ph.D. Ph.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 127 pages eng Massachusetts Institute of Technology 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. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Representation and transfer learning using information-theoretic approximations Thesis application/pdf 2020-09-03T17:41:36Z Publication Doctoral EECS unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1c542644-b6ef-472d-8718-370d5d0989d6"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Representation and transfer learning using information-theoretic approximations</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <Authors> <Author> <DisplayName>Qiu, David.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <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> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>