{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-classifiers-with-fenchel-young","title":"Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms","arxiv_id":"1805.09717","date":"2018-05-24","proceeding":null,"authors":["Mathieu Blondel","André F. T. Martins","Vlad Niculae"],"abstract":"This paper studies Fenchel-Young losses, a generic way to construct convex\nloss functions from a regularization function. We analyze their properties in\ndepth, showing that they unify many well-known loss functions and allow to\ncreate useful new ones easily. Fenchel-Young losses constructed from a\ngeneralized entropy, including the Shannon and Tsallis entropies, induce\npredictive probability distributions. We formulate conditions for a generalized\nentropy to yield losses with a separation margin, and probability distributions\nwith sparse support. Finally, we derive efficient algorithms, making\nFenchel-Young losses appealing both in theory and practice.","url_abs":"http://arxiv.org/abs/1805.09717v4","url_pdf":"http://arxiv.org/pdf/1805.09717v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-classifiers-with-fenchel-young","repo_url":"https://github.com/mblondel/fenchel-young-losses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-classifiers-with-fenchel-young","repo_url":"https://github.com/mblondel/projection-losses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.09717","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}