{"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/unifying-distillation-and-privileged","title":"Unifying distillation and privileged information","arxiv_id":"1511.03643","date":"2015-11-11","proceeding":null,"authors":["David Lopez-Paz","Léon Bottou","Bernhard Schölkopf","Vladimir Vapnik"],"abstract":"Distillation (Hinton et al., 2015) and privileged information (Vapnik &\nIzmailov, 2015) are two techniques that enable machines to learn from other\nmachines. This paper unifies these two techniques into generalized\ndistillation, a framework to learn from multiple machines and data\nrepresentations. We provide theoretical and causal insight about the inner\nworkings of generalized distillation, extend it to unsupervised, semisupervised\nand multitask learning scenarios, and illustrate its efficacy on a variety of\nnumerical simulations on both synthetic and real-world data.","url_abs":"http://arxiv.org/abs/1511.03643v3","url_pdf":"http://arxiv.org/pdf/1511.03643v3.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":"unifying-distillation-and-privileged","repo_url":"https://github.com/lopezpaz/distillation_privileged_information","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.03643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.03643"}},"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/lopezpaz/distillation_privileged_information","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"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":"55c02f0770fe2193","entry":"weighted_loss","repo":"lopezpaz/distillation_privileged_information","repo_kind":"listed","path":"code/sarcos.py","file_url":"https://github.com/lopezpaz/distillation_privileged_information/blob/HEAD/code/sarcos.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55c02f0770fe2193"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}