{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/152788"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/152788","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Conformal Methods for Efficient and Reliable Deep Learning","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_html":"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_has_math":false,"creators":["Fisch, Adam"],"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":["Barzilay, Regina","Jaakkola, Tommi"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-09","date_published":"2023-09","updated_at":"2026-07-22T22:21:51Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/152788","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Barzilay, Regina","Jaakkola, Tommi"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Fisch, Adam"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-11-02T20:16:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-11-02T20:16:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-09"]},{"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","Doctor of Philosophy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/152788"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Conformal Methods for Efficient and Reliable Deep Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Barzilay, Regina","Jaakkola, Tommi"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Fisch, Adam"],"dc:date.accessioned":["2023-11-02T20:16:18Z"],"dc:date.available":["2023-11-02T20:16:18Z"],"dc:date.issued":["2023-09"],"dc:description.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."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/152788"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Conformal Methods for Efficient and Reliable Deep Learning"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral","Doctor of Philosophy"]},"updated_at":"2026-07-22T22:21:51Z"}