{"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/scalable-bayesian-rule-lists","title":"Scalable Bayesian Rule Lists","arxiv_id":"1602.08610","date":"2016-02-27","proceeding":"ICML 2017 8","authors":["Hongyu Yang","Cynthia Rudin","Margo Seltzer"],"abstract":"We present an algorithm for building probabilistic rule lists that is two\norders of magnitude faster than previous work. Rule list algorithms are\ncompetitors for decision tree algorithms. They are associative classifiers, in\nthat they are built from pre-mined association rules. They have a logical\nstructure that is a sequence of IF-THEN rules, identical to a decision list or\none-sided decision tree. Instead of using greedy splitting and pruning like\ndecision tree algorithms, we fully optimize over rule lists, striking a\npractical balance between accuracy, interpretability, and computational speed.\nThe algorithm presented here uses a mixture of theoretical bounds (tight enough\nto have practical implications as a screening or bounding procedure),\ncomputational reuse, and highly tuned language libraries to achieve\ncomputational efficiency. Currently, for many practical problems, this method\nachieves better accuracy and sparsity than decision trees; further, in many\ncases, the computational time is practical and often less than that of decision\ntrees. The result is a probabilistic classifier (which estimates P(y = 1|x) for\neach x) that optimizes the posterior of a Bayesian hierarchical model over rule\nlists.","url_abs":"http://arxiv.org/abs/1602.08610v2","url_pdf":"http://arxiv.org/pdf/1602.08610v2.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":"scalable-bayesian-rule-lists","repo_url":"https://github.com/corels/corels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"scalable-bayesian-rule-lists","repo_url":"https://github.com/corels/rcppcorels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"scalable-bayesian-rule-lists","repo_url":"https://github.com/csinva/imodels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"scalable-bayesian-rule-lists","repo_url":"https://github.com/eddelbuettel/rcppcorels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"scalable-bayesian-rule-lists","repo_url":"https://github.com/nlarusstone/corels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"scalable-bayesian-rule-lists","repo_url":"https://github.com/fingoldin/pycorels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"scalable-bayesian-rule-lists","repo_url":"https://github.com/saligrama/rcorels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1602.08610","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}