{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZONFNP6THJODN4ZOHD2OQCST3A","short_pith_number":"pith:ZONFNP6T","schema_version":"1.0","canonical_sha256":"cb9a56bfd33a5c36f32e38f4e80a53d808f164fd7223fcc25b7f2f9ba57a9254","source":{"kind":"arxiv","id":"2211.15118","version":2},"attestation_state":"computed","paper":{"title":"A Faster $k$-means++ Algorithm","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Chenbo Yin, Danyang Zhuo, Jiehao Liang, Junze Yin, Somdeb Sarkhel, Zhao Song","submitted_at":"2022-11-28T08:17:12Z","abstract_excerpt":"$k$-means++ is an important algorithm for choosing initial cluster centers for the $k$-means clustering algorithm. In this work, we present a new algorithm that can solve the $k$-means++ problem with nearly optimal running time. Given $n$ data points in $\\mathbb{R}^d$, the current state-of-the-art algorithm runs in $\\widetilde{O}(k )$ iterations, and each iteration takes $\\widetilde{O}(nd k)$ time. The overall running time is thus $\\widetilde{O}(n d k^2)$. We propose a new algorithm \\textsc{FastKmeans++} that only takes in $\\widetilde{O}(nd + nk^2)$ time, in total."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.15118","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DS","submitted_at":"2022-11-28T08:17:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"146fb2f37cd69c536732865ea56993ba08d7a11473ba3921a2f08d77c556ef54","abstract_canon_sha256":"73b3542f9582aef888250e496ab1c1c617e42e40555fd36ebc5235240d327c7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:51.981245Z","signature_b64":"KaB4nZasYKObpNAdX1SlW0YSL2QoPklQoc2OoF/BsMJfTVWtqJINbwC/aIxeqSJIvW2hGZA4XykN5Bas6gIcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb9a56bfd33a5c36f32e38f4e80a53d808f164fd7223fcc25b7f2f9ba57a9254","last_reissued_at":"2026-07-05T07:44:51.980848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:51.980848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Faster $k$-means++ Algorithm","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Chenbo Yin, Danyang Zhuo, Jiehao Liang, Junze Yin, Somdeb Sarkhel, Zhao Song","submitted_at":"2022-11-28T08:17:12Z","abstract_excerpt":"$k$-means++ is an important algorithm for choosing initial cluster centers for the $k$-means clustering algorithm. In this work, we present a new algorithm that can solve the $k$-means++ problem with nearly optimal running time. Given $n$ data points in $\\mathbb{R}^d$, the current state-of-the-art algorithm runs in $\\widetilde{O}(k )$ iterations, and each iteration takes $\\widetilde{O}(nd k)$ time. The overall running time is thus $\\widetilde{O}(n d k^2)$. We propose a new algorithm \\textsc{FastKmeans++} that only takes in $\\widetilde{O}(nd + nk^2)$ time, in total."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15118","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.15118/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.15118","created_at":"2026-07-05T07:44:51.980913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15118v2","created_at":"2026-07-05T07:44:51.980913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15118","created_at":"2026-07-05T07:44:51.980913+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZONFNP6THJOD","created_at":"2026-07-05T07:44:51.980913+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZONFNP6THJODN4ZO","created_at":"2026-07-05T07:44:51.980913+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZONFNP6T","created_at":"2026-07-05T07:44:51.980913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06167","citing_title":"Universal Approximation of Visual Autoregressive Transformers","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A","json":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A.json","graph_json":"https://pith.science/api/pith-number/ZONFNP6THJODN4ZOHD2OQCST3A/graph.json","events_json":"https://pith.science/api/pith-number/ZONFNP6THJODN4ZOHD2OQCST3A/events.json","paper":"https://pith.science/paper/ZONFNP6T"},"agent_actions":{"view_html":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A","download_json":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A.json","view_paper":"https://pith.science/paper/ZONFNP6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15118&json=true","fetch_graph":"https://pith.science/api/pith-number/ZONFNP6THJODN4ZOHD2OQCST3A/graph.json","fetch_events":"https://pith.science/api/pith-number/ZONFNP6THJODN4ZOHD2OQCST3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A/action/storage_attestation","attest_author":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A/action/author_attestation","sign_citation":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A/action/citation_signature","submit_replication":"https://pith.science/pith/ZONFNP6THJODN4ZOHD2OQCST3A/action/replication_record"}},"created_at":"2026-07-05T07:44:51.980913+00:00","updated_at":"2026-07-05T07:44:51.980913+00:00"}