{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LPU7BFPNFPDW7F6T2PVG5KI7OD","short_pith_number":"pith:LPU7BFPN","schema_version":"1.0","canonical_sha256":"5be9f095ed2bc76f97d3d3ea6ea91f70c12e46f932d2c5eefa29f01d6bceff68","source":{"kind":"arxiv","id":"1611.00519","version":2},"attestation_state":"computed","paper":{"title":"On the Convergence of the EM Algorithm: A Data-Adaptive Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Can Yang, Chong Wu, Hongyu Zhao, Ji Zhu","submitted_at":"2016-11-02T09:35:30Z","abstract_excerpt":"The Expectation-Maximization (EM) algorithm is an iterative method to maximize the log-likelihood function for parameter estimation. Previous works on the convergence analysis of the EM algorithm have established results on the asymptotic (population level) convergence rate of the algorithm. In this paper, we give a data-adaptive analysis of the sample level local convergence rate of the EM algorithm. In particular, we show that the local convergence rate of the EM algorithm is a random variable $\\overline{K}_{n}$ derived from the data generating distribution, which adaptively yields the conve"},"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":"1611.00519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-11-02T09:35:30Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"3885dbd6aa9d6354a4509ab24434ca2df4059cd2fe74bd6cc0419e23ac86290f","abstract_canon_sha256":"a642ceb6bc081827424bd4b3157cc10235a0e179c9455bb6bfffc092f72e1b8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:30.097842Z","signature_b64":"Wu8lgkvyttJT5jfkLBrS/9H/+DpXfeJ8YhEDdmBg/ZNytTGEpaJGLByu4SZCvRQKd3476SrlMLm7/W2ZJczcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5be9f095ed2bc76f97d3d3ea6ea91f70c12e46f932d2c5eefa29f01d6bceff68","last_reissued_at":"2026-05-18T00:43:30.097189Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:30.097189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of the EM Algorithm: A Data-Adaptive Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Can Yang, Chong Wu, Hongyu Zhao, Ji Zhu","submitted_at":"2016-11-02T09:35:30Z","abstract_excerpt":"The Expectation-Maximization (EM) algorithm is an iterative method to maximize the log-likelihood function for parameter estimation. Previous works on the convergence analysis of the EM algorithm have established results on the asymptotic (population level) convergence rate of the algorithm. In this paper, we give a data-adaptive analysis of the sample level local convergence rate of the EM algorithm. In particular, we show that the local convergence rate of the EM algorithm is a random variable $\\overline{K}_{n}$ derived from the data generating distribution, which adaptively yields the conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00519","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":""},"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":"1611.00519","created_at":"2026-05-18T00:43:30.097289+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00519v2","created_at":"2026-05-18T00:43:30.097289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00519","created_at":"2026-05-18T00:43:30.097289+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPU7BFPNFPDW","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPU7BFPNFPDW7F6T","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPU7BFPN","created_at":"2026-05-18T12:30:29.479603+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/LPU7BFPNFPDW7F6T2PVG5KI7OD","json":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD.json","graph_json":"https://pith.science/api/pith-number/LPU7BFPNFPDW7F6T2PVG5KI7OD/graph.json","events_json":"https://pith.science/api/pith-number/LPU7BFPNFPDW7F6T2PVG5KI7OD/events.json","paper":"https://pith.science/paper/LPU7BFPN"},"agent_actions":{"view_html":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD","download_json":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD.json","view_paper":"https://pith.science/paper/LPU7BFPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00519&json=true","fetch_graph":"https://pith.science/api/pith-number/LPU7BFPNFPDW7F6T2PVG5KI7OD/graph.json","fetch_events":"https://pith.science/api/pith-number/LPU7BFPNFPDW7F6T2PVG5KI7OD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD/action/storage_attestation","attest_author":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD/action/author_attestation","sign_citation":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD/action/citation_signature","submit_replication":"https://pith.science/pith/LPU7BFPNFPDW7F6T2PVG5KI7OD/action/replication_record"}},"created_at":"2026-05-18T00:43:30.097289+00:00","updated_at":"2026-05-18T00:43:30.097289+00:00"}