{"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/contrastive-pessimistic-likelihood-estimation","title":"Contrastive Pessimistic Likelihood Estimation for Semi-Supervised Classification","arxiv_id":"1503.00269","date":"2015-03-01","proceeding":null,"authors":["Marco Loog"],"abstract":"Improvement guarantees for semi-supervised classifiers can currently only be\ngiven under restrictive conditions on the data. We propose a general way to\nperform semi-supervised parameter estimation for likelihood-based classifiers\nfor which, on the full training set, the estimates are never worse than the\nsupervised solution in terms of the log-likelihood. We argue, moreover, that we\nmay expect these solutions to really improve upon the supervised classifier in\nparticular cases. In a worked-out example for LDA, we take it one step further\nand essentially prove that its semi-supervised version is strictly better than\nits supervised counterpart. The two new concepts that form the core of our\nestimation principle are contrast and pessimism. The former refers to the fact\nthat our objective function takes the supervised estimates into account,\nenabling the semi-supervised solution to explicitly control the potential\nimprovements over this estimate. The latter refers to the fact that our\nestimates are conservative and therefore resilient to whatever form the true\nlabeling of the unlabeled data takes on. Experiments demonstrate the\nimprovements in terms of both the log-likelihood and the classification error\nrate on independent test sets.","url_abs":"http://arxiv.org/abs/1503.00269v2","url_pdf":"http://arxiv.org/pdf/1503.00269v2.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":"contrastive-pessimistic-likelihood-estimation","repo_url":"https://github.com/BorisovDm/CPLE_SSL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[{"method_slug":"lda","method_name":"LDA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.00269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.00269"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/BorisovDm/CPLE_SSL","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"fffaafa235b3a87c","entry":"class_cov","repo":"BorisovDm/CPLE_SSL","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/BorisovDm/CPLE_SSL/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fffaafa235b3a87c"}},{"code_sha256_prefix":"d085a26c6b08fa1f","entry":"class_means","repo":"BorisovDm/CPLE_SSL","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/BorisovDm/CPLE_SSL/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d085a26c6b08fa1f"}},{"code_sha256_prefix":"db83f3a3d4f7c604","entry":"softmax","repo":"BorisovDm/CPLE_SSL","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/BorisovDm/CPLE_SSL/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"db83f3a3d4f7c604"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}