{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TAQ7IUDS5YTXSTBE6BWR3EIDBX","short_pith_number":"pith:TAQ7IUDS","schema_version":"1.0","canonical_sha256":"9821f45072ee27794c24f06d1d91030ddd9ac3c24232369601129702b726d0f6","source":{"kind":"arxiv","id":"2005.10817","version":3},"attestation_state":"computed","paper":{"title":"Computationally efficient sparse clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Afonso S. Bandeira, Alexander S. Wein, Matthias L\\\"offler","submitted_at":"2020-05-21T17:51:30Z","abstract_excerpt":"We study statistical and computational limits of clustering when the means of the centres are sparse and their dimension is possibly much larger than the sample size. Our theoretical analysis focuses on the model $X_i = z_i \\theta + \\varepsilon_i, ~z_i \\in \\{-1,1\\}, ~\\varepsilon_i \\thicksim \\mathcal{N}(0,I)$, which has two clusters with centres $\\theta$ and $-\\theta$. We provide a finite sample analysis of a new sparse clustering algorithm based on sparse PCA and show that it achieves the minimax optimal misclustering rate in the regime $\\|\\theta\\| \\rightarrow \\infty$.\n  Our results require th"},"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":"2005.10817","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-05-21T17:51:30Z","cross_cats_sorted":["cs.CC","cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"f294e4208e87914ad390265686a37303694803e02c89d158ba29a568c7c47cf5","abstract_canon_sha256":"88b4c0fa71b19456bd583b5dace07d07bebeeaea7d545d05489800fa2d88cb26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:10.224934Z","signature_b64":"0LcArO+RJvi7Huygu64Wgox63H7uHbmuDCr0Mk+d8CGzX+czuVM+150YEvLwzYPiVg9nrI1O+Q4kspbGgqgKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9821f45072ee27794c24f06d1d91030ddd9ac3c24232369601129702b726d0f6","last_reissued_at":"2026-07-05T02:25:10.224530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:10.224530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computationally efficient sparse clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Afonso S. Bandeira, Alexander S. Wein, Matthias L\\\"offler","submitted_at":"2020-05-21T17:51:30Z","abstract_excerpt":"We study statistical and computational limits of clustering when the means of the centres are sparse and their dimension is possibly much larger than the sample size. Our theoretical analysis focuses on the model $X_i = z_i \\theta + \\varepsilon_i, ~z_i \\in \\{-1,1\\}, ~\\varepsilon_i \\thicksim \\mathcal{N}(0,I)$, which has two clusters with centres $\\theta$ and $-\\theta$. We provide a finite sample analysis of a new sparse clustering algorithm based on sparse PCA and show that it achieves the minimax optimal misclustering rate in the regime $\\|\\theta\\| \\rightarrow \\infty$.\n  Our results require th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10817","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.10817/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":"2005.10817","created_at":"2026-07-05T02:25:10.224585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10817v3","created_at":"2026-07-05T02:25:10.224585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10817","created_at":"2026-07-05T02:25:10.224585+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAQ7IUDS5YTX","created_at":"2026-07-05T02:25:10.224585+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAQ7IUDS5YTXSTBE","created_at":"2026-07-05T02:25:10.224585+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAQ7IUDS","created_at":"2026-07-05T02:25:10.224585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17360","citing_title":"The Quasi-Polynomial Low-Degree Conjecture is False","ref_index":73,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX","json":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX.json","graph_json":"https://pith.science/api/pith-number/TAQ7IUDS5YTXSTBE6BWR3EIDBX/graph.json","events_json":"https://pith.science/api/pith-number/TAQ7IUDS5YTXSTBE6BWR3EIDBX/events.json","paper":"https://pith.science/paper/TAQ7IUDS"},"agent_actions":{"view_html":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX","download_json":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX.json","view_paper":"https://pith.science/paper/TAQ7IUDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10817&json=true","fetch_graph":"https://pith.science/api/pith-number/TAQ7IUDS5YTXSTBE6BWR3EIDBX/graph.json","fetch_events":"https://pith.science/api/pith-number/TAQ7IUDS5YTXSTBE6BWR3EIDBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX/action/storage_attestation","attest_author":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX/action/author_attestation","sign_citation":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX/action/citation_signature","submit_replication":"https://pith.science/pith/TAQ7IUDS5YTXSTBE6BWR3EIDBX/action/replication_record"}},"created_at":"2026-07-05T02:25:10.224585+00:00","updated_at":"2026-07-05T02:25:10.224585+00:00"}