{"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/extrapolating-expected-accuracies-for-large","title":"Extrapolating Expected Accuracies for Large Multi-Class Problems","arxiv_id":"1712.09713","date":"2017-12-27","proceeding":null,"authors":["Charles Zheng","Rakesh Achanta","Yuval Benjamini"],"abstract":"The difficulty of multi-class classification generally increases with the\nnumber of classes. Using data from a subset of the classes, can we predict how\nwell a classifier will scale with an increased number of classes? Under the\nassumptions that the classes are sampled identically and independently from a\npopulation, and that the classifier is based on independently learned scoring\nfunctions, we show that the expected accuracy when the classifier is trained on\nk classes is the (k-1)st moment of a certain distribution that can be estimated\nfrom data. We present an unbiased estimation method based on the theory, and\ndemonstrate its application on a facial recognition example.","url_abs":"http://arxiv.org/abs/1712.09713v1","url_pdf":"http://arxiv.org/pdf/1712.09713v1.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":"extrapolating-expected-accuracies-for-large","repo_url":"https://github.com/snarles/ClassEx","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}