{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/151827"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/151827","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Consistent Estimators for Learning to Defer to an Expert","abstract":"Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however, this fact is largely ignored when designing these algorithms. In this thesis, we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert's decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks.","abstract_html":"Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however, this fact is largely ignored when designing these algorithms. In this thesis, we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert's decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks.","abstract_has_math":false,"creators":["Mozannar, Hussein"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Institute for Data, Systems, and Society","school":null,"contributors":[],"advisors":["Sontag, David"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06","date_published":"2023-06","updated_at":"2026-07-22T22:21:01Z","subjects":[],"languages":[],"rights":["Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)","Copyright retained by author(s)"],"rights_urls":["https://creativecommons.org/licenses/by-sa/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/151827","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Sontag, David"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Institute for Data, Systems, and Society"]},{"key":"dc:creator","label":"Author","values":["Mozannar, Hussein"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-08-23T16:11:39Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-08-23T16:11:39Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06"]},{"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":["Master","Master of Science in Social and Engineering Systems"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/151827"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however, this fact is largely ignored when designing these algorithms. In this thesis, we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert's decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Consistent Estimators for Learning to Defer to an Expert"]}]}],"canonical_facts":{"dc:contributor.advisor":["Sontag, David"],"dc:contributor.department":["Massachusetts Institute of Technology. Institute for Data, Systems, and Society"],"dc:creator":["Mozannar, Hussein"],"dc:date.accessioned":["2023-08-23T16:11:39Z"],"dc:date.available":["2023-08-23T16:11:39Z"],"dc:date.issued":["2023-06"],"dc:description.abstract":["Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however, this fact is largely ignored when designing these algorithms. In this thesis, we explore how to learn predictors that can either predict or choose to defer the decision to a downstream expert. Given only samples of the expert's decisions, we give a procedure based on learning a classifier and a rejector and analyze it theoretically. Our approach is based on a novel reduction to cost sensitive learning where we give a consistent surrogate loss for cost sensitive learning that generalizes the cross entropy loss. We show the effectiveness of our approach on a variety of experimental tasks."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/151827"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)","Copyright retained by author(s)"],"dc:rights.uri":["https://creativecommons.org/licenses/by-sa/4.0/"],"dc:title":["Consistent Estimators for Learning to Defer to an Expert"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Social and Engineering Systems"]},"updated_at":"2026-07-22T22:21:01Z"}