{"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/on-the-minimal-supervision-for-training-any","title":"On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data","arxiv_id":"1808.10585","date":"2018-08-31","proceeding":"ICLR 2019 5","authors":["Nan Lu","Gang Niu","Aditya Krishna Menon","Masashi Sugiyama"],"abstract":"Empirical risk minimization (ERM), with proper loss function and\nregularization, is the common practice of supervised classification. In this\npaper, we study training arbitrary (from linear to deep) binary classifier from\nonly unlabeled (U) data by ERM. We prove that it is impossible to estimate the\nrisk of an arbitrary binary classifier in an unbiased manner given a single set\nof U data, but it becomes possible given two sets of U data with different\nclass priors. These two facts answer a fundamental question---what the minimal\nsupervision is for training any binary classifier from only U data. Following\nthese findings, we propose an ERM-based learning method from two sets of U\ndata, and then prove it is consistent. Experiments demonstrate the proposed\nmethod could train deep models and outperform state-of-the-art methods for\nlearning from two sets of U data.","url_abs":"http://arxiv.org/abs/1808.10585v4","url_pdf":"http://arxiv.org/pdf/1808.10585v4.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":"on-the-minimal-supervision-for-training-any","repo_url":"https://github.com/lunanbit/UUlearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.10585","atlas_url":"https://app.syntology.ai/?focus=1808.10585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10585"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lunanbit/UUlearning","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"ff7e03c8ff06e25d","entry":"build_file_name","repo":"lunanbit/UUlearning","repo_kind":"official","path":"experiment.py","file_url":"https://github.com/lunanbit/UUlearning/blob/HEAD/experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff7e03c8ff06e25d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}