{"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/influence-functions-for-machine-learning","title":"Influence Functions for Machine Learning: Nonparametric Estimators for Entropies, Divergences and Mutual Informations","arxiv_id":"1411.4342","date":"2014-11-17","proceeding":null,"authors":["Kirthevasan Kandasamy","Akshay Krishnamurthy","Barnabas Poczos","Larry Wasserman","James M. Robins"],"abstract":"We propose and analyze estimators for statistical functionals of one or more\ndistributions under nonparametric assumptions. Our estimators are based on the\ntheory of influence functions, which appear in the semiparametric statistics\nliterature. We show that estimators based either on data-splitting or a\nleave-one-out technique enjoy fast rates of convergence and other favorable\ntheoretical properties. We apply this framework to derive estimators for\nseveral popular information theoretic quantities, and via empirical evaluation,\nshow the advantage of this approach over existing estimators.","url_abs":"http://arxiv.org/abs/1411.4342v3","url_pdf":"http://arxiv.org/pdf/1411.4342v3.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":"influence-functions-for-machine-learning","repo_url":"https://github.com/kirthevasank/if-estimators","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"influence-functions-for-machine-learning","repo_url":"https://github.com/matthewvowels1/generalizing_IFs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1411.4342","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}