{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FLIU7SO54TZPY5CVOKLFSLBZ4T","short_pith_number":"pith:FLIU7SO5","schema_version":"1.0","canonical_sha256":"2ad14fc9dde4f2fc74557296592c39e4ee1964343ba40c61507b798d1bc1a939","source":{"kind":"arxiv","id":"2305.17224","version":2},"attestation_state":"computed","paper":{"title":"Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Gavin Zhang, Hong-Ming Chiu, Richard Y. Zhang","submitted_at":"2023-05-26T19:32:07Z","abstract_excerpt":"Non-convex gradient descent is a common approach for estimating a low-rank $n\\times n$ ground truth matrix from noisy measurements, because it has per-iteration costs as low as $O(n)$ time, and is in theory capable of converging to a minimax optimal estimate. However, the practitioner is often constrained to just tens to hundreds of iterations, and the slow and/or inconsistent convergence of non-convex gradient descent can prevent a high-quality estimate from being obtained. Recently, the technique of preconditioning was shown to be highly effective at accelerating the local convergence of non"},"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":"2305.17224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-05-26T19:32:07Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6242f926e425a2a259d2c560510eeaa7172d13818ea247f6a7fea70d3000e6df","abstract_canon_sha256":"4160c7313d86df708453a10498ffb4054a0e3bc180be3851f271406d04e7d9fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:01.571548Z","signature_b64":"/jwVX/jsjKvYZ23pd8k8zRlvZJQ8wX/kzMdDpWok1kLeTVaPWv6LuTOzvAW7uddyZ4SOLQ/V0mU1RiA5kGZxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad14fc9dde4f2fc74557296592c39e4ee1964343ba40c61507b798d1bc1a939","last_reissued_at":"2026-07-05T07:50:01.571123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:01.571123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Gavin Zhang, Hong-Ming Chiu, Richard Y. Zhang","submitted_at":"2023-05-26T19:32:07Z","abstract_excerpt":"Non-convex gradient descent is a common approach for estimating a low-rank $n\\times n$ ground truth matrix from noisy measurements, because it has per-iteration costs as low as $O(n)$ time, and is in theory capable of converging to a minimax optimal estimate. However, the practitioner is often constrained to just tens to hundreds of iterations, and the slow and/or inconsistent convergence of non-convex gradient descent can prevent a high-quality estimate from being obtained. Recently, the technique of preconditioning was shown to be highly effective at accelerating the local convergence of non"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17224","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/2305.17224/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":"2305.17224","created_at":"2026-07-05T07:50:01.571182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17224v2","created_at":"2026-07-05T07:50:01.571182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17224","created_at":"2026-07-05T07:50:01.571182+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLIU7SO54TZP","created_at":"2026-07-05T07:50:01.571182+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLIU7SO54TZPY5CV","created_at":"2026-07-05T07:50:01.571182+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLIU7SO5","created_at":"2026-07-05T07:50:01.571182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20659","citing_title":"A High-Dimensional Statistical Theory for Convex and Nonconvex Matrix Sensing","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T","json":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T.json","graph_json":"https://pith.science/api/pith-number/FLIU7SO54TZPY5CVOKLFSLBZ4T/graph.json","events_json":"https://pith.science/api/pith-number/FLIU7SO54TZPY5CVOKLFSLBZ4T/events.json","paper":"https://pith.science/paper/FLIU7SO5"},"agent_actions":{"view_html":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T","download_json":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T.json","view_paper":"https://pith.science/paper/FLIU7SO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17224&json=true","fetch_graph":"https://pith.science/api/pith-number/FLIU7SO54TZPY5CVOKLFSLBZ4T/graph.json","fetch_events":"https://pith.science/api/pith-number/FLIU7SO54TZPY5CVOKLFSLBZ4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T/action/storage_attestation","attest_author":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T/action/author_attestation","sign_citation":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T/action/citation_signature","submit_replication":"https://pith.science/pith/FLIU7SO54TZPY5CVOKLFSLBZ4T/action/replication_record"}},"created_at":"2026-07-05T07:50:01.571182+00:00","updated_at":"2026-07-05T07:50:01.571182+00:00"}