{"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/an-empirical-evaluation-of-k-means-coresets","title":"An Empirical Evaluation of $k$-Means Coresets","arxiv_id":"2207.00966","date":"2022-07-03","proceeding":null,"authors":["Chris Schwiegelshohn","Omar Ali Sheikh-Omar"],"abstract":"Coresets are among the most popular paradigms for summarizing data. In particular, there exist many high performance coresets for clustering problems such as $k$-means in both theory and practice. Curiously, there exists no work on comparing the quality of available $k$-means coresets. In this paper we perform such an evaluation. There currently is no algorithm known to measure the distortion of a candidate coreset. We provide some evidence as to why this might be computationally difficult. To complement this, we propose a benchmark for which we argue that computing coresets is challenging and which also allows us an easy (heuristic) evaluation of coresets. Using this benchmark and real-world data sets, we conduct an exhaustive evaluation of the most commonly used coreset algorithms from theory and practice.","url_abs":"https://arxiv.org/abs/2207.00966v1","url_pdf":"https://arxiv.org/pdf/2207.00966v1.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":"an-empirical-evaluation-of-k-means-coresets","repo_url":"https://github.com/sheikhomar/eval-k-means-coresets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"}],"methods":[{"method_slug":"coresets","method_name":"Coresets"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.00966","atlas_url":"https://app.syntology.ai/?focus=2207.00966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00966"}},"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/sheikhomar/eval-k-means-coresets","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"8bd0f0d1b1b6aef1","entry":"compute_coreset_center_cost","repo":"sheikhomar/eval-k-means-coresets","repo_kind":"official","path":"xrun/calc_cc_costs.py","file_url":"https://github.com/sheikhomar/eval-k-means-coresets/blob/HEAD/xrun/calc_cc_costs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bd0f0d1b1b6aef1"}},{"code_sha256_prefix":"c0a23f7fb1b5bfa4","entry":"find_unprocesses_run_files","repo":"sheikhomar/eval-k-means-coresets","repo_kind":"official","path":"xrun/calc_cc_costs.py","file_url":"https://github.com/sheikhomar/eval-k-means-coresets/blob/HEAD/xrun/calc_cc_costs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0a23f7fb1b5bfa4"}},{"code_sha256_prefix":"78f1872ab2eb722a","entry":"unzip_file","repo":"sheikhomar/eval-k-means-coresets","repo_kind":"official","path":"xrun/calc_costs.py","file_url":"https://github.com/sheikhomar/eval-k-means-coresets/blob/HEAD/xrun/calc_costs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"78f1872ab2eb722a"}},{"code_sha256_prefix":"68e69499b706d8a5","entry":"unzip_file","repo":"sheikhomar/eval-k-means-coresets","repo_kind":"official","path":"xrun/eval_benchmark.py","file_url":"https://github.com/sheikhomar/eval-k-means-coresets/blob/HEAD/xrun/eval_benchmark.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"68e69499b706d8a5"}},{"code_sha256_prefix":"94bcb1646b7a880a","entry":"validate_algorithms","repo":"sheikhomar/eval-k-means-coresets","repo_kind":"official","path":"xrun/gen.py","file_url":"https://github.com/sheikhomar/eval-k-means-coresets/blob/HEAD/xrun/gen.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94bcb1646b7a880a"}},{"code_sha256_prefix":"0889a2c52cadc86a","entry":"validate_datasets","repo":"sheikhomar/eval-k-means-coresets","repo_kind":"official","path":"xrun/gen.py","file_url":"https://github.com/sheikhomar/eval-k-means-coresets/blob/HEAD/xrun/gen.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0889a2c52cadc86a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}