{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JXFUPBHPNW64ZJA2SYOVSX7TIY","short_pith_number":"pith:JXFUPBHP","schema_version":"1.0","canonical_sha256":"4dcb4784ef6dbdcca41a961d595ff34603e05bb2766ae709b4fb711e69a9b189","source":{"kind":"arxiv","id":"1908.10935","version":1},"attestation_state":"computed","paper":{"title":"Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in $O(\\sqrt{n})$ iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Harrison H. Zhou, Yihong Wu","submitted_at":"2019-08-28T20:44:19Z","abstract_excerpt":"We analyze the classical EM algorithm for parameter estimation in the symmetric two-component Gaussian mixtures in $d$ dimensions. We show that, even in the absence of any separation between components, provided that the sample size satisfies $n=\\Omega(d \\log^3 d)$, the randomly initialized EM algorithm converges to an estimate in at most $O(\\sqrt{n})$ iterations with high probability, which is at most $O((\\frac{d \\log^3 n}{n})^{1/4})$ in Euclidean distance from the true parameter and within logarithmic factors of the minimax rate of $(\\frac{d}{n})^{1/4}$. Both the nonparametric statistical ra"},"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":"1908.10935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-08-28T20:44:19Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML","stat.TH"],"title_canon_sha256":"1b15fd740c1a612f17999e26506758345de968462821c8f380c0aa4a9280a6b9","abstract_canon_sha256":"f415de025d2fdcb8eb219df865c1ba1bec897393f958a4d488a97ac5f65fe91d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:28.709923Z","signature_b64":"tW+BFgf79V5bmlm5xlG1P9nRW6OR2vqW3TcxUuDaGCfosjRnAHlEL9qsXN2gWnDd4piYDpsVtMqrd3ZbRCQWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dcb4784ef6dbdcca41a961d595ff34603e05bb2766ae709b4fb711e69a9b189","last_reissued_at":"2026-07-05T00:00:28.709453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:28.709453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in $O(\\sqrt{n})$ iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Harrison H. Zhou, Yihong Wu","submitted_at":"2019-08-28T20:44:19Z","abstract_excerpt":"We analyze the classical EM algorithm for parameter estimation in the symmetric two-component Gaussian mixtures in $d$ dimensions. We show that, even in the absence of any separation between components, provided that the sample size satisfies $n=\\Omega(d \\log^3 d)$, the randomly initialized EM algorithm converges to an estimate in at most $O(\\sqrt{n})$ iterations with high probability, which is at most $O((\\frac{d \\log^3 n}{n})^{1/4})$ in Euclidean distance from the true parameter and within logarithmic factors of the minimax rate of $(\\frac{d}{n})^{1/4}$. Both the nonparametric statistical ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10935","kind":"arxiv","version":1},"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/1908.10935/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":"1908.10935","created_at":"2026-07-05T00:00:28.709511+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10935v1","created_at":"2026-07-05T00:00:28.709511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10935","created_at":"2026-07-05T00:00:28.709511+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXFUPBHPNW64","created_at":"2026-07-05T00:00:28.709511+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXFUPBHPNW64ZJA2","created_at":"2026-07-05T00:00:28.709511+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXFUPBHP","created_at":"2026-07-05T00:00:28.709511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03240","citing_title":"On Model-Based Clustering With Entropic Optimal Transport","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY","json":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY.json","graph_json":"https://pith.science/api/pith-number/JXFUPBHPNW64ZJA2SYOVSX7TIY/graph.json","events_json":"https://pith.science/api/pith-number/JXFUPBHPNW64ZJA2SYOVSX7TIY/events.json","paper":"https://pith.science/paper/JXFUPBHP"},"agent_actions":{"view_html":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY","download_json":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY.json","view_paper":"https://pith.science/paper/JXFUPBHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10935&json=true","fetch_graph":"https://pith.science/api/pith-number/JXFUPBHPNW64ZJA2SYOVSX7TIY/graph.json","fetch_events":"https://pith.science/api/pith-number/JXFUPBHPNW64ZJA2SYOVSX7TIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY/action/storage_attestation","attest_author":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY/action/author_attestation","sign_citation":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY/action/citation_signature","submit_replication":"https://pith.science/pith/JXFUPBHPNW64ZJA2SYOVSX7TIY/action/replication_record"}},"created_at":"2026-07-05T00:00:28.709511+00:00","updated_at":"2026-07-05T00:00:28.709511+00:00"}