{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MWRKAAB42HHMCFQ4LXR6HID3E7","short_pith_number":"pith:MWRKAAB4","schema_version":"1.0","canonical_sha256":"65a2a0003cd1cec1161c5de3e3a07b27d98fba3c48976ea05ba9e46dee4bbb38","source":{"kind":"arxiv","id":"1711.11247","version":3},"attestation_state":"computed","paper":{"title":"Provably noise-robust, regularised $k$-means clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shai Ben-David, Shrinu Kushagra, Yaoliang Yu","submitted_at":"2017-11-30T06:23:52Z","abstract_excerpt":"We consider the problem of clustering in the presence of noise. That is, when on top of cluster structure, the data also contains a subset of \\emph{unstructured} points. Our goal is to detect the clusters despite the presence of many unstructured points. Any algorithm that achieves this goal is noise-robust. We consider a regularisation method which converts any center-based clustering objective into a noise-robust one. We focus on the $k$-means objective and we prove that the regularised version of $k$-means is NP-Hard even for $k=1$. We consider two algorithms based on the convex (sdp and lp"},"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":"1711.11247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-30T06:23:52Z","cross_cats_sorted":[],"title_canon_sha256":"e2e8b20b32da9a4e6328fc6563c0a74eb8b29ecb41e19a86306564c98d5ba9cd","abstract_canon_sha256":"7dab7942fdd83788b71939be89a72820d945ecb2fd2b8c25bfc9c66b2ad3de22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:18.192728Z","signature_b64":"dLnpF0buDWen/VvpFJiiFMZCzWt30vJU0nHvTQGgLhufg2y1b3T05OaUcvTcrqnybk3AAbM62UK/IbP1v57fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65a2a0003cd1cec1161c5de3e3a07b27d98fba3c48976ea05ba9e46dee4bbb38","last_reissued_at":"2026-05-18T00:07:18.192009Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:18.192009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably noise-robust, regularised $k$-means clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shai Ben-David, Shrinu Kushagra, Yaoliang Yu","submitted_at":"2017-11-30T06:23:52Z","abstract_excerpt":"We consider the problem of clustering in the presence of noise. That is, when on top of cluster structure, the data also contains a subset of \\emph{unstructured} points. Our goal is to detect the clusters despite the presence of many unstructured points. Any algorithm that achieves this goal is noise-robust. We consider a regularisation method which converts any center-based clustering objective into a noise-robust one. We focus on the $k$-means objective and we prove that the regularised version of $k$-means is NP-Hard even for $k=1$. We consider two algorithms based on the convex (sdp and lp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11247","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.11247","created_at":"2026-05-18T00:07:18.192119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11247v3","created_at":"2026-05-18T00:07:18.192119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11247","created_at":"2026-05-18T00:07:18.192119+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWRKAAB42HHM","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWRKAAB42HHMCFQ4","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWRKAAB4","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7","json":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7.json","graph_json":"https://pith.science/api/pith-number/MWRKAAB42HHMCFQ4LXR6HID3E7/graph.json","events_json":"https://pith.science/api/pith-number/MWRKAAB42HHMCFQ4LXR6HID3E7/events.json","paper":"https://pith.science/paper/MWRKAAB4"},"agent_actions":{"view_html":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7","download_json":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7.json","view_paper":"https://pith.science/paper/MWRKAAB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11247&json=true","fetch_graph":"https://pith.science/api/pith-number/MWRKAAB42HHMCFQ4LXR6HID3E7/graph.json","fetch_events":"https://pith.science/api/pith-number/MWRKAAB42HHMCFQ4LXR6HID3E7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7/action/storage_attestation","attest_author":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7/action/author_attestation","sign_citation":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7/action/citation_signature","submit_replication":"https://pith.science/pith/MWRKAAB42HHMCFQ4LXR6HID3E7/action/replication_record"}},"created_at":"2026-05-18T00:07:18.192119+00:00","updated_at":"2026-05-18T00:07:18.192119+00:00"}