{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4J37WRRFJXQTMKMRA7IWNDDAJ4","short_pith_number":"pith:4J37WRRF","schema_version":"1.0","canonical_sha256":"e277fb46254de136299107d1668c604f0d4ffde1801d6516587db1d11e7459a2","source":{"kind":"arxiv","id":"1804.00795","version":2},"attestation_state":"computed","paper":{"title":"Estimation of Markov Chain via Rank-Constrained Likelihood","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Anru Zhang, Mengdi Wang, Xudong Li","submitted_at":"2018-04-03T02:28:47Z","abstract_excerpt":"This paper studies the estimation of low-rank Markov chains from empirical trajectories. We propose a non-convex estimator based on rank-constrained likelihood maximization. Statistical upper bounds are provided for the Kullback-Leiber divergence and the $\\ell_2$ risk between the estimator and the true transition matrix. The estimator reveals a compressed state space of the Markov chain. We also develop a novel DC (difference of convex function) programming algorithm to tackle the rank-constrained non-smooth optimization problem. Convergence results are established. Experiments show that the p"},"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":"1804.00795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-03T02:28:47Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"3a9c8de0fcf7148e74458e681376155877912097f96e941407b957077e4626ee","abstract_canon_sha256":"23f3bf100ed08072e4252149ac83e6301e834c302de1eb6e0d473e95db8d2a3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:21.909977Z","signature_b64":"HfKGzXOU4sUPdmMCKgXq6iu5jZg2tQW9TtRs5GEY0R96yu03osTHTbShO3sORiUdhC1xacl/EtEkwqRbk/+aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e277fb46254de136299107d1668c604f0d4ffde1801d6516587db1d11e7459a2","last_reissued_at":"2026-05-18T00:10:21.909522Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:21.909522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimation of Markov Chain via Rank-Constrained Likelihood","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Anru Zhang, Mengdi Wang, Xudong Li","submitted_at":"2018-04-03T02:28:47Z","abstract_excerpt":"This paper studies the estimation of low-rank Markov chains from empirical trajectories. We propose a non-convex estimator based on rank-constrained likelihood maximization. Statistical upper bounds are provided for the Kullback-Leiber divergence and the $\\ell_2$ risk between the estimator and the true transition matrix. The estimator reveals a compressed state space of the Markov chain. We also develop a novel DC (difference of convex function) programming algorithm to tackle the rank-constrained non-smooth optimization problem. Convergence results are established. Experiments show that the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00795","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":"1804.00795","created_at":"2026-05-18T00:10:21.909589+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.00795v2","created_at":"2026-05-18T00:10:21.909589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00795","created_at":"2026-05-18T00:10:21.909589+00:00"},{"alias_kind":"pith_short_12","alias_value":"4J37WRRFJXQT","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4J37WRRFJXQTMKMR","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4J37WRRF","created_at":"2026-05-18T12:32:05.422762+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/4J37WRRFJXQTMKMRA7IWNDDAJ4","json":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4.json","graph_json":"https://pith.science/api/pith-number/4J37WRRFJXQTMKMRA7IWNDDAJ4/graph.json","events_json":"https://pith.science/api/pith-number/4J37WRRFJXQTMKMRA7IWNDDAJ4/events.json","paper":"https://pith.science/paper/4J37WRRF"},"agent_actions":{"view_html":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4","download_json":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4.json","view_paper":"https://pith.science/paper/4J37WRRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.00795&json=true","fetch_graph":"https://pith.science/api/pith-number/4J37WRRFJXQTMKMRA7IWNDDAJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/4J37WRRFJXQTMKMRA7IWNDDAJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4/action/storage_attestation","attest_author":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4/action/author_attestation","sign_citation":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4/action/citation_signature","submit_replication":"https://pith.science/pith/4J37WRRFJXQTMKMRA7IWNDDAJ4/action/replication_record"}},"created_at":"2026-05-18T00:10:21.909589+00:00","updated_at":"2026-05-18T00:10:21.909589+00:00"}