{"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-credible-models","title":"Learning Credible Models","arxiv_id":"1711.03190","date":"2017-11-08","proceeding":null,"authors":["Jiaxuan Wang","Jeeheh Oh","Haozhu Wang","Jenna Wiens"],"abstract":"In many settings, it is important that a model be capable of providing\nreasons for its predictions (i.e., the model must be interpretable). However,\nthe model's reasoning may not conform with well-established knowledge. In such\ncases, while interpretable, the model lacks \\textit{credibility}. In this work,\nwe formally define credibility in the linear setting and focus on techniques\nfor learning models that are both accurate and credible. In particular, we\npropose a regularization penalty, expert yielded estimates (EYE), that\nincorporates expert knowledge about well-known relationships among covariates\nand the outcome of interest. We give both theoretical and empirical results\ncomparing our proposed method to several other regularization techniques.\nAcross a range of settings, experiments on both synthetic and real data show\nthat models learned using the EYE penalty are significantly more credible than\nthose learned using other penalties. Applied to a large-scale patient risk\nstratification task, our proposed technique results in a model whose top\nfeatures overlap significantly with known clinical risk factors, while still\nachieving good predictive performance.","url_abs":"http://arxiv.org/abs/1711.03190v3","url_pdf":"http://arxiv.org/pdf/1711.03190v3.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-credible-models","repo_url":"https://github.com/nathanwang000/credible_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}