{"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/learning-optimal-representations-with-the","title":"Learning Optimal Representations with the Decodable Information Bottleneck","arxiv_id":"2009.12789","date":"2020-09-27","proceeding":"NeurIPS 2020 12","authors":["Yann Dubois","Douwe Kiela","David J. Schwab","Ramakrishna Vedantam"],"abstract":"We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information about the targets, in a decoder-agnostic fashion. In machine learning, however, our goal is not compression but rather generalization, which is intimately linked to the predictive family or decoder of interest (e.g. linear classifier). We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. As a result, DIB gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees. Empirically, we show that the framework can be used to enforce a small generalization gap on downstream classifiers and to predict the generalization ability of neural networks.","url_abs":"https://arxiv.org/abs/2009.12789v2","url_pdf":"https://arxiv.org/pdf/2009.12789v2.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":"learning-optimal-representations-with-the","repo_url":"https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.12789","atlas_url":"https://app.syntology.ai/?focus=2009.12789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12789"}},"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":"deterministic:regex_extraction","url":"https://github.com/YannDubs/Overlayed-Datasets","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck","reach":null}],"summary":{"ran":1,"ran_violates":1,"unverified":5},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1},"found_in_text":{"samples":3,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"7802df85cbd95114","entry":"NaiveNuisanceGetter","repo":"YannDubs/Mini_Decodable_Information_Bottleneck","repo_kind":"official","path":"dib.py","file_url":"https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck/blob/HEAD/dib.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7802df85cbd95114"}},{"code_sha256_prefix":"65f37b6c0e79c62c","entry":"mean","repo":"YannDubs/Mini_Decodable_Information_Bottleneck","repo_kind":"official","path":"dib.py","file_url":"https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck/blob/HEAD/dib.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65f37b6c0e79c62c"}},{"code_sha256_prefix":"92826fcdb76a58f7","entry":"DIBLoss","repo":"YannDubs/Mini_Decodable_Information_Bottleneck","repo_kind":"official","path":"dib.py","file_url":"https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck/blob/HEAD/dib.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92826fcdb76a58f7"}},{"code_sha256_prefix":"28cfdd5104c56715","entry":"ScaleGrad","repo":"YannDubs/Mini_Decodable_Information_Bottleneck","repo_kind":"official","path":"dib.py","file_url":"https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck/blob/HEAD/dib.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"28cfdd5104c56715"}},{"code_sha256_prefix":"3d9933391cdf0451","entry":"at_least_ndim","repo":"YannDubs/Overlayed-Datasets","repo_kind":"found_in_text","path":"overlay.py","file_url":"https://github.com/YannDubs/Overlayed-Datasets/blob/HEAD/overlay.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d9933391cdf0451"}},{"code_sha256_prefix":"645e40ccfbeaea8e","entry":"ensure_color","repo":"YannDubs/Overlayed-Datasets","repo_kind":"found_in_text","path":"overlay.py","file_url":"https://github.com/YannDubs/Overlayed-Datasets/blob/HEAD/overlay.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"645e40ccfbeaea8e"}},{"code_sha256_prefix":"b6de5dcb962518af","entry":"overlay_img","repo":"YannDubs/Overlayed-Datasets","repo_kind":"found_in_text","path":"overlay.py","file_url":"https://github.com/YannDubs/Overlayed-Datasets/blob/HEAD/overlay.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6de5dcb962518af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}