{"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-diverse-and-discriminative","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","arxiv_id":"2006.08558","date":"2020-06-15","proceeding":"NeurIPS 2020 12","authors":["Yaodong Yu","Kwan Ho Ryan Chan","Chong You","Chaobing Song","Yi Ma"],"abstract":"To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction ($\\text{MCR}^2$), an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class. We clarify its relationships with most existing frameworks such as cross-entropy, information bottleneck, information gain, contractive and contrastive learning, and provide theoretical guarantees for learning diverse and discriminative features. The coding rate can be accurately computed from finite samples of degenerate subspace-like distributions and can learn intrinsic representations in supervised, self-supervised, and unsupervised settings in a unified manner. Empirically, the representations learned using this principle alone are significantly more robust to label corruptions in classification than those using cross-entropy, and can lead to state-of-the-art results in clustering mixed data from self-learned invariant features.","url_abs":"https://arxiv.org/abs/2006.08558v1","url_pdf":"https://arxiv.org/pdf/2006.08558v1.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-diverse-and-discriminative","repo_url":"https://github.com/ryanchankh/mcr2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-diverse-and-discriminative","repo_url":"https://github.com/Ma-Lab-Berkeley/MCR2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"image-clustering","task_name":"Image Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-stl-10","task":"Image Clustering","dataset":"STL-10","model":"MCR2","rank_in_archive_order":23,"of":29,"metrics":{"Accuracy":"0.491","NMI":"0.446"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.08558","atlas_url":"https://app.syntology.ai/?focus=2006.08558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08558"}},"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/Ma-Lab-Berkeley/MCR2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ryanchankh/mcr2","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"bac061dbcd471695","entry":"svm","repo":"ryanchankh/mcr2","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/ryanchankh/mcr2/blob/HEAD/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bac061dbcd471695"}},{"code_sha256_prefix":"25a77ab10668ae65","entry":"load_architectures","repo":"ryanchankh/mcr2","repo_kind":"official","path":"train_func.py","file_url":"https://github.com/ryanchankh/mcr2/blob/HEAD/train_func.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25a77ab10668ae65"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}