2026-09-19T15:02:23Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1270142026-06-17T14:42:55Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Justin Solomon.
Claici, Sebastian.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2020-09-03T17:41:55Z
2020-09-03T17:41:55Z
2020
2020
https://hdl.handle.net/1721.1/127014
1191624382
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 169-187).
The typical machine learning algorithms looks for a pattern in data, and makes an assumption that the signal to noise ratio of the pattern is high. This approach depends strongly on the quality of the datasets these algorithms operate on, and many complex algorithms fail in spectacular fashion on simple tasks by overfitting noise or outlier examples. These algorithms have training procedures that scale poorly in the size of the dataset, and their out-puts are difficult to intepret. This thesis proposes solutions to both problems by leveraging the theory of optimal transport and proposing efficient algorithms to solve problems in: (1) quantization, with extensions to the Wasserstein barycenter problem, and a link to the classical coreset problem; (2) natural language processing where the hierarchical structure of text allows us to compare documents efficiently;(3) Bayesian inference where we can impose a hierarchy on the label switching problem to resolve ambiguities.
by Sebastian Claici.
Ph.D.
Ph.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
187 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.
Structure as simplification : transportation tools for understanding data
Transportation tools for understanding data
Thesis
application/pdf
2020-09-03T17:41:55Z
Publication
Doctoral
EECS
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="70099fc1-fe2d-4b53-99c8-26fcd2831d61">
<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>Structure as simplification : transportation tools for understanding data</Title>
<Subtitle>Transportation tools for understanding data</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2020</PublicationDate>
<Authors>
<Author>
<DisplayName>Claici, Sebastian.</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>The typical machine learning algorithms looks for a pattern in data, and makes an assumption that the signal to noise ratio of the pattern is high. This approach depends strongly on the quality of the datasets these algorithms operate on, and many complex algorithms fail in spectacular fashion on simple tasks by overfitting noise or outlier examples. These algorithms have training procedures that scale poorly in the size of the dataset, and their out-puts are difficult to intepret. This thesis proposes solutions to both problems by leveraging the theory of optimal transport and proposing efficient algorithms to solve problems in: (1) quantization, with extensions to the Wasserstein barycenter problem, and a link to the classical coreset problem; (2) natural language processing where the hierarchical structure of text allows us to compare documents efficiently;(3) Bayesian inference where we can impose a hierarchy on the label switching problem to resolve ambiguities.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>