2026-09-19T10:48:47Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1527882023-11-03T03:29:09Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Barzilay, Regina
Jaakkola, Tommi
Fisch, Adam
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2023-11-02T20:16:18Z
2023-11-02T20:16:18Z
2023-09
2023-09-21T14:26:21.483Z
https://hdl.handle.net/1721.1/152788
Deep learning has seen exciting progress over the last decade. As large foundation models continue to evolve and be deployed into real-life applications, an important question to ask is how we can make these expensive, inscrutable models more efficient and reliable. In this thesis, we present a number of fundamental techniques for building and deploying effective deep learning systems that are broadly based on conformal prediction, a model-agnostic and distribution-free uncertainty estimation framework. We develop both theory and practice for leveraging uncertainty estimation to build adaptive models that are cheaper to run, have desirable performance guarantees, and are general enough to work well in many real-world scenarios. Empirically, we primarily focus on natural language processing (NLP) applications, together with substantial extensions to tasks in computer vision, drug discovery, and medicine.
Ph.D.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Conformal Methods for Efficient and Reliable Deep Learning
Thesis
application/pdf
Doctoral
Doctor of Philosophy
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="9e090d0a-8d7b-43b4-845c-f741bc4a7b85">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Conformal Methods for Efficient and Reliable Deep Learning</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2023-09</PublicationDate>
<Authors>
<Author>
<DisplayName>Fisch, Adam</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Deep learning has seen exciting progress over the last decade. As large foundation models continue to evolve and be deployed into real-life applications, an important question to ask is how we can make these expensive, inscrutable models more efficient and reliable. In this thesis, we present a number of fundamental techniques for building and deploying effective deep learning systems that are broadly based on conformal prediction, a model-agnostic and distribution-free uncertainty estimation framework. We develop both theory and practice for leveraging uncertainty estimation to build adaptive models that are cheaper to run, have desirable performance guarantees, and are general enough to work well in many real-world scenarios. Empirically, we primarily focus on natural language processing (NLP) applications, together with substantial extensions to tasks in computer vision, drug discovery, and medicine.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>