{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BYD4LIIWF6KXZ73QSQFL54AZDT","short_pith_number":"pith:BYD4LIIW","schema_version":"1.0","canonical_sha256":"0e07c5a1162f957cff70940abef0191cea0b4c81f99214a1efa20d285dfc2634","source":{"kind":"arxiv","id":"1702.07933","version":3},"attestation_state":"computed","paper":{"title":"Efficient Learning of Mixed Membership Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sayan Mukherjee, Zilong Tan","submitted_at":"2017-02-25T18:00:57Z","abstract_excerpt":"We present an efficient algorithm for learning mixed membership models when the number of variables $p$ is much larger than the number of hidden components $k$. This algorithm reduces the computational complexity of state-of-the-art tensor methods, which require decomposing an $O\\left(p^3\\right)$ tensor, to factorizing $O\\left(p/k\\right)$ sub-tensors each of size $O\\left(k^3\\right)$. In addition, we address the issue of negative entries in the empirical method of moments based estimators. We provide sufficient conditions under which our approach has provable guarantees. Our approach obtains co"},"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":"1702.07933","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-25T18:00:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7156001fba465620894be96b6c65807854afddf20e10d271c0e908bcfa21a51e","abstract_canon_sha256":"d4537cc31a947d102f2a3271d93571c1264caf43dcbe06bbc18ee8a72e026324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:07.330807Z","signature_b64":"8/Y0VTlnt37ok8qB3Z8j4rUqaCAVDEdnfZBLLbpyilYF8+9KRFvBHjyikqtq4aPuS1zCuxQShSX3tRtJwWZ5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e07c5a1162f957cff70940abef0191cea0b4c81f99214a1efa20d285dfc2634","last_reissued_at":"2026-05-18T00:41:07.330298Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:07.330298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Learning of Mixed Membership Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Sayan Mukherjee, Zilong Tan","submitted_at":"2017-02-25T18:00:57Z","abstract_excerpt":"We present an efficient algorithm for learning mixed membership models when the number of variables $p$ is much larger than the number of hidden components $k$. This algorithm reduces the computational complexity of state-of-the-art tensor methods, which require decomposing an $O\\left(p^3\\right)$ tensor, to factorizing $O\\left(p/k\\right)$ sub-tensors each of size $O\\left(k^3\\right)$. In addition, we address the issue of negative entries in the empirical method of moments based estimators. We provide sufficient conditions under which our approach has provable guarantees. Our approach obtains co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07933","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":""},"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":"1702.07933","created_at":"2026-05-18T00:41:07.330378+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07933v3","created_at":"2026-05-18T00:41:07.330378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07933","created_at":"2026-05-18T00:41:07.330378+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYD4LIIWF6KX","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYD4LIIWF6KXZ73Q","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYD4LIIW","created_at":"2026-05-18T12:31:08.081275+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/BYD4LIIWF6KXZ73QSQFL54AZDT","json":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT.json","graph_json":"https://pith.science/api/pith-number/BYD4LIIWF6KXZ73QSQFL54AZDT/graph.json","events_json":"https://pith.science/api/pith-number/BYD4LIIWF6KXZ73QSQFL54AZDT/events.json","paper":"https://pith.science/paper/BYD4LIIW"},"agent_actions":{"view_html":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT","download_json":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT.json","view_paper":"https://pith.science/paper/BYD4LIIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07933&json=true","fetch_graph":"https://pith.science/api/pith-number/BYD4LIIWF6KXZ73QSQFL54AZDT/graph.json","fetch_events":"https://pith.science/api/pith-number/BYD4LIIWF6KXZ73QSQFL54AZDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT/action/storage_attestation","attest_author":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT/action/author_attestation","sign_citation":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT/action/citation_signature","submit_replication":"https://pith.science/pith/BYD4LIIWF6KXZ73QSQFL54AZDT/action/replication_record"}},"created_at":"2026-05-18T00:41:07.330378+00:00","updated_at":"2026-05-18T00:41:07.330378+00:00"}