{"id":{"repo_id":"bu","oai_identifier":"oai:open.bu.edu:2144/43719"},"canonical_url":"https://search.ndltd.org/etd/bu/oai:open.bu.edu:2144/43719","repository":{"repo_id":"bu","name":"Boston University","base_url":"https://open.bu.edu/oai/request"},"display":{"title":"Convex regression and its extensions to learning a Bregman divergence and difference of convex functions","abstract":"Nonparametric convex regression has been extensively studied over the last two decades. It has been shown any Lipschitz convex function can be approximated with arbitrarily accuracy with a max of linear functions. Using this framework, in this thesis we generalize convex regression to learning an arbitrary Bregman divergence and learning a difference of convex functions. We provide approximation guarantees and sample complexity bounds for both these extensions. Furthermore, we provide algorithms to solve the resulting optimization problems based on 2-block alternative direction method of multipliers (ADMM). For this algorithm, we provide convergence guarantees with iteration complexity of O(n√d/𝜖) for a dataset X 𝝐 ℝ^n,d and arbitrary positive 𝜖. Finally we provide experiments for both the Bregman divergence learning and difference of convex functions learning based on UCI datasets that demonstrate the state of the art on regression and classification datasets.","abstract_html":"Nonparametric convex regression has been extensively studied over the last two decades. It has been shown any Lipschitz convex function can be approximated with arbitrarily accuracy with a max of linear functions. Using this framework, in this thesis we generalize convex regression to learning an arbitrary Bregman divergence and learning a difference of convex functions. We provide approximation guarantees and sample complexity bounds for both these extensions. Furthermore, we provide algorithms to solve the resulting optimization problems based on 2-block alternative direction method of multipliers (ADMM). For this algorithm, we provide convergence guarantees with iteration complexity of O(n√d/𝜖) for a dataset X 𝝐 ℝ^n,d and arbitrary positive 𝜖. Finally we provide experiments for both the Bregman divergence learning and difference of convex functions learning based on UCI datasets that demonstrate the state of the art on regression and classification datasets.","abstract_has_math":false,"creators":["Siahkamari, Ali"],"institution":"Boston University","degree_name":"Doctor of Philosophy","degree_level":"doctoral","degree_discipline":"Electrical & Computer Engineering","degree_department":null,"school":null,"contributors":[],"advisors":["Kulis, Brian","Saligrama, Venkatesh"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022","date_published":"2022","updated_at":"2026-11-18T20:34:05Z","subjects":["Statistics","ADMM","Bregman divergence","Convex regression","Difference of convex","Piecewise linear regression"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2144/43719","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/2144/43719","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://open.bu.edu/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aopen.bu.edu%3A2144%2F43719","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kulis, Brian","Saligrama, Venkatesh"]},{"key":"dc:creator","label":"Author","values":["Siahkamari, Ali"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-01-29T15:54:23Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-01-29T15:54:23Z"]},{"key":"dc:date.issued","label":"Date","values":["2022"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2022-01-26T23:07:48Z"]},{"key":"dc:type","label":"Dc Type","values":["Thesis/Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Boston University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Statistics","ADMM","Bregman divergence","Convex regression","Difference of convex","Piecewise linear regression"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2144/43719"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Nonparametric convex regression has been extensively studied over the last two decades. It has been shown any Lipschitz convex function can be approximated with arbitrarily accuracy with a max of linear functions. Using this framework, in this thesis we generalize convex regression to learning an arbitrary Bregman divergence and learning a difference of convex functions. We provide approximation guarantees and sample complexity bounds for both these extensions. Furthermore, we provide algorithms to solve the resulting optimization problems based on 2-block alternative direction method of multipliers (ADMM). For this algorithm, we provide convergence guarantees with iteration complexity of O(n√d/𝜖) for a dataset X 𝝐 ℝ^n,d and arbitrary positive 𝜖. Finally we provide experiments for both the Bregman divergence learning and difference of convex functions learning based on UCI datasets that demonstrate the state of the art on regression and classification datasets."]},{"key":"dc:title","label":"Title","values":["Convex regression and its extensions to learning a Bregman divergence and difference of convex functions"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kulis, Brian","Saligrama, Venkatesh"],"dc:creator":["Siahkamari, Ali"],"dc:date.accessioned":["2022-01-29T15:54:23Z"],"dc:date.available":["2022-01-29T15:54:23Z"],"dc:date.issued":["2022"],"dc:date.updated":["2022-01-26T23:07:48Z"],"dc:description.abstract":["Nonparametric convex regression has been extensively studied over the last two decades. It has been shown any Lipschitz convex function can be approximated with arbitrarily accuracy with a max of linear functions. Using this framework, in this thesis we generalize convex regression to learning an arbitrary Bregman divergence and learning a difference of convex functions. We provide approximation guarantees and sample complexity bounds for both these extensions. Furthermore, we provide algorithms to solve the resulting optimization problems based on 2-block alternative direction method of multipliers (ADMM). For this algorithm, we provide convergence guarantees with iteration complexity of O(n√d/𝜖) for a dataset X 𝝐 ℝ^n,d and arbitrary positive 𝜖. Finally we provide experiments for both the Bregman divergence learning and difference of convex functions learning based on UCI datasets that demonstrate the state of the art on regression and classification datasets."],"dc:identifier.uri":["https://hdl.handle.net/2144/43719"],"dc:language.iso":["en_US"],"dc:subject":["Statistics","ADMM","Bregman divergence","Convex regression","Difference of convex","Piecewise linear regression"],"dc:title":["Convex regression and its extensions to learning a Bregman divergence and difference of convex functions"],"dc:type":["Thesis/Dissertation"],"thesis:degree_discipline":["Electrical & Computer Engineering"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Boston University"]},"updated_at":"2026-11-18T20:34:05Z"}