{"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/discovering-structure-in-high-dimensional","title":"Discovering Structure in High-Dimensional Data Through Correlation Explanation","arxiv_id":"1406.1222","date":"2014-06-04","proceeding":"NeurIPS 2014 12","authors":["Greg Ver Steeg","Aram Galstyan"],"abstract":"We introduce a method to learn a hierarchy of successively more abstract\nrepresentations of complex data based on optimizing an information-theoretic\nobjective. Intuitively, the optimization searches for a set of latent factors\nthat best explain the correlations in the data as measured by multivariate\nmutual information. The method is unsupervised, requires no model assumptions,\nand scales linearly with the number of variables which makes it an attractive\napproach for very high dimensional systems. We demonstrate that Correlation\nExplanation (CorEx) automatically discovers meaningful structure for data from\ndiverse sources including personality tests, DNA, and human language.","url_abs":"http://arxiv.org/abs/1406.1222v2","url_pdf":"http://arxiv.org/pdf/1406.1222v2.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":"discovering-structure-in-high-dimensional","repo_url":"https://github.com/gregversteeg/CorEx","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-2.0"}},{"paper_slug":"discovering-structure-in-high-dimensional","repo_url":"https://github.com/gregversteeg/corex_topic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"discovering-structure-in-high-dimensional","repo_url":"https://github.com/gregversteeg/discrete_sieve","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.1222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1406.1222"}},"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/gregversteeg/CorEx","reach":{"status":"ok","spdx":"GPL-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gregversteeg/discrete_sieve","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gregversteeg/corex_topic","reach":null}],"summary":{"ran_violates":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":0,"samples":[{"code_sha256_prefix":"71aa163beb20ff2a","entry":"binary_entropy","repo":"gregversteeg/corex_topic","repo_kind":"listed","path":"corextopic/corextopic.py","file_url":"https://github.com/gregversteeg/corex_topic/blob/HEAD/corextopic/corextopic.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71aa163beb20ff2a"}},{"code_sha256_prefix":"a835ad6c5a19a10c","entry":"flatten","repo":"gregversteeg/corex_topic","repo_kind":"listed","path":"corextopic/corextopic.py","file_url":"https://github.com/gregversteeg/corex_topic/blob/HEAD/corextopic/corextopic.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a835ad6c5a19a10c"}},{"code_sha256_prefix":"e9140664116c595f","entry":"log_1mp","repo":"gregversteeg/corex_topic","repo_kind":"listed","path":"corextopic/corextopic.py","file_url":"https://github.com/gregversteeg/corex_topic/blob/HEAD/corextopic/corextopic.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e9140664116c595f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}