{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IKV7WI2MISU2GQOMZEFGNB4RPL","short_pith_number":"pith:IKV7WI2M","schema_version":"1.0","canonical_sha256":"42abfb234c44a9a341ccc90a6687917ae551dbb4be09affb0b1d4368e80ae775","source":{"kind":"arxiv","id":"1902.00194","version":4},"attestation_state":"computed","paper":{"title":"Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Bin Yu, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan, Nhat Ho, Raaz Dwivedi","submitted_at":"2019-02-01T06:07:08Z","abstract_excerpt":"We study a class of weakly identifiable location-scale mixture models for which the maximum likelihood estimates based on $n$ i.i.d. samples are known to have lower accuracy than the classical $n^{- \\frac{1}{2}}$ error. We investigate whether the Expectation-Maximization (EM) algorithm also converges slowly for these models. We provide a rigorous characterization of EM for fitting a weakly identifiable Gaussian mixture in a univariate setting where we prove that the EM algorithm converges in order $n^{\\frac{3}{4}}$ steps and returns estimates that are at a Euclidean distance of order ${ n^{- \\"},"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":"1902.00194","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-02-01T06:07:08Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"9aba840f6637cd0928e109ccdbe55eb08a7494f6a3774fccb2cdd527b3f34b9d","abstract_canon_sha256":"4d877b502838dc817fb3e5239b82e678715580d810cbd32b53028d074f0762c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:51.138760Z","signature_b64":"6c1gYnJO+yHwgV7sX/OpUmsQNCKMJ7eQyjId6WTy2hscJB6ixYsaVQl579B4bBPVUTs3X+4l+LnOsk2XsvQ9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42abfb234c44a9a341ccc90a6687917ae551dbb4be09affb0b1d4368e80ae775","last_reissued_at":"2026-07-05T03:31:51.138225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:51.138225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Bin Yu, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan, Nhat Ho, Raaz Dwivedi","submitted_at":"2019-02-01T06:07:08Z","abstract_excerpt":"We study a class of weakly identifiable location-scale mixture models for which the maximum likelihood estimates based on $n$ i.i.d. samples are known to have lower accuracy than the classical $n^{- \\frac{1}{2}}$ error. We investigate whether the Expectation-Maximization (EM) algorithm also converges slowly for these models. We provide a rigorous characterization of EM for fitting a weakly identifiable Gaussian mixture in a univariate setting where we prove that the EM algorithm converges in order $n^{\\frac{3}{4}}$ steps and returns estimates that are at a Euclidean distance of order ${ n^{- \\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00194","kind":"arxiv","version":4},"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/1902.00194/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":"1902.00194","created_at":"2026-07-05T03:31:51.138292+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00194v4","created_at":"2026-07-05T03:31:51.138292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00194","created_at":"2026-07-05T03:31:51.138292+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKV7WI2MISU2","created_at":"2026-07-05T03:31:51.138292+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKV7WI2MISU2GQOM","created_at":"2026-07-05T03:31:51.138292+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKV7WI2M","created_at":"2026-07-05T03:31:51.138292+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/IKV7WI2MISU2GQOMZEFGNB4RPL","json":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL.json","graph_json":"https://pith.science/api/pith-number/IKV7WI2MISU2GQOMZEFGNB4RPL/graph.json","events_json":"https://pith.science/api/pith-number/IKV7WI2MISU2GQOMZEFGNB4RPL/events.json","paper":"https://pith.science/paper/IKV7WI2M"},"agent_actions":{"view_html":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL","download_json":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL.json","view_paper":"https://pith.science/paper/IKV7WI2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00194&json=true","fetch_graph":"https://pith.science/api/pith-number/IKV7WI2MISU2GQOMZEFGNB4RPL/graph.json","fetch_events":"https://pith.science/api/pith-number/IKV7WI2MISU2GQOMZEFGNB4RPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL/action/storage_attestation","attest_author":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL/action/author_attestation","sign_citation":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL/action/citation_signature","submit_replication":"https://pith.science/pith/IKV7WI2MISU2GQOMZEFGNB4RPL/action/replication_record"}},"created_at":"2026-07-05T03:31:51.138292+00:00","updated_at":"2026-07-05T03:31:51.138292+00:00"}