{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VHHKPG7AJEGGHSRYIHPTXCPS6I","short_pith_number":"pith:VHHKPG7A","schema_version":"1.0","canonical_sha256":"a9cea79be0490c63ca3841df3b89f2f2106e9f6df0339a807b9dc4f4ccde6d05","source":{"kind":"arxiv","id":"1905.12106","version":2},"attestation_state":"computed","paper":{"title":"EM Converges for a Mixture of Many Linear Regressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Jeongyeol Kwon","submitted_at":"2019-05-28T21:51:48Z","abstract_excerpt":"We study the convergence of the Expectation-Maximization (EM) algorithm for mixtures of linear regressions with an arbitrary number $k$ of components. We show that as long as signal-to-noise ratio (SNR) is $\\tilde{\\Omega}(k)$, well-initialized EM converges to the true regression parameters. Previous results for $k \\geq 3$ have only established local convergence for the noiseless setting, i.e., where SNR is infinitely large. Our results enlarge the scope to the environment with noises, and notably, we establish a statistical error rate that is independent of the norm (or pairwise distance) of t"},"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":"1905.12106","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T21:51:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9c8c5cc54d01d723ce6e288fcb738cf619e228426daf217f3ead024c2f102fd0","abstract_canon_sha256":"c598ae9e81013867ebf91b591e22cf26e2f0aab72eb9dd3ed46da065f7d588e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:58.311562Z","signature_b64":"LQQYmYvgfWQqJ51x/jgreD2tIBlMGzrGtK9eu/aANFRLVjnYoBcrHTmkBLNvvRu43eoeNy0fKGopDs4sJHdNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9cea79be0490c63ca3841df3b89f2f2106e9f6df0339a807b9dc4f4ccde6d05","last_reissued_at":"2026-07-05T00:21:58.311115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:58.311115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EM Converges for a Mixture of Many Linear Regressions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Jeongyeol Kwon","submitted_at":"2019-05-28T21:51:48Z","abstract_excerpt":"We study the convergence of the Expectation-Maximization (EM) algorithm for mixtures of linear regressions with an arbitrary number $k$ of components. We show that as long as signal-to-noise ratio (SNR) is $\\tilde{\\Omega}(k)$, well-initialized EM converges to the true regression parameters. Previous results for $k \\geq 3$ have only established local convergence for the noiseless setting, i.e., where SNR is infinitely large. Our results enlarge the scope to the environment with noises, and notably, we establish a statistical error rate that is independent of the norm (or pairwise distance) of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12106","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.12106/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":"1905.12106","created_at":"2026-07-05T00:21:58.311179+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12106v2","created_at":"2026-07-05T00:21:58.311179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12106","created_at":"2026-07-05T00:21:58.311179+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHHKPG7AJEGG","created_at":"2026-07-05T00:21:58.311179+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHHKPG7AJEGGHSRY","created_at":"2026-07-05T00:21:58.311179+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHHKPG7A","created_at":"2026-07-05T00:21:58.311179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11547","citing_title":"Linearly Solving Robust Rotation Estimation","ref_index":82,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I","json":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I.json","graph_json":"https://pith.science/api/pith-number/VHHKPG7AJEGGHSRYIHPTXCPS6I/graph.json","events_json":"https://pith.science/api/pith-number/VHHKPG7AJEGGHSRYIHPTXCPS6I/events.json","paper":"https://pith.science/paper/VHHKPG7A"},"agent_actions":{"view_html":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I","download_json":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I.json","view_paper":"https://pith.science/paper/VHHKPG7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12106&json=true","fetch_graph":"https://pith.science/api/pith-number/VHHKPG7AJEGGHSRYIHPTXCPS6I/graph.json","fetch_events":"https://pith.science/api/pith-number/VHHKPG7AJEGGHSRYIHPTXCPS6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I/action/storage_attestation","attest_author":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I/action/author_attestation","sign_citation":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I/action/citation_signature","submit_replication":"https://pith.science/pith/VHHKPG7AJEGGHSRYIHPTXCPS6I/action/replication_record"}},"created_at":"2026-07-05T00:21:58.311179+00:00","updated_at":"2026-07-05T00:21:58.311179+00:00"}