{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ILWN2KGJBWMDISRS6BQR3ANNHJ","short_pith_number":"pith:ILWN2KGJ","schema_version":"1.0","canonical_sha256":"42ecdd28c90d98344a32f0611d81ad3a6c66366c577f4c2687466a9bec2189d1","source":{"kind":"arxiv","id":"2406.14211","version":1},"attestation_state":"computed","paper":{"title":"Optimization over bounded-rank matrices through a desingularization enables joint global and local guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Nicolas Boumal, Quentin Rebjock","submitted_at":"2024-06-20T11:26:57Z","abstract_excerpt":"Convergence guarantees for optimization over bounded-rank matrices are delicate to obtain because the feasible set is a non-smooth and non-convex algebraic variety. Existing techniques include projected gradient descent, fixed-rank optimization (over the maximal-rank stratum), and the LR parameterization. They all lack either global guarantees (the ability to accumulate only at critical points) or fast local convergence (e.g., if the limit has non-maximal rank). We seek optimization algorithms that enjoy both.\n  Khrulkov and Oseledets [2018] parameterize the bounded-rank variety via a desingul"},"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":"2406.14211","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-20T11:26:57Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"3f92b88db34acca73d22a03315eaf8a28fbb8b168b4b69e97960ac9362a7fbb5","abstract_canon_sha256":"f4b6a6bde0e53c4bc779c647f9f117ff36abd7dd97bd6f5850810116eb0c60c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:40.482291Z","signature_b64":"b0ADGPOIATE0WI7JnmOrJIpivwckczrx7UyAKQJHA43vxgSDHAfqTLjwnMJ3hx4rjnFyI9MpolI0SoT9d7LNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ecdd28c90d98344a32f0611d81ad3a6c66366c577f4c2687466a9bec2189d1","last_reissued_at":"2026-07-05T08:34:40.481860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:40.481860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimization over bounded-rank matrices through a desingularization enables joint global and local guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Nicolas Boumal, Quentin Rebjock","submitted_at":"2024-06-20T11:26:57Z","abstract_excerpt":"Convergence guarantees for optimization over bounded-rank matrices are delicate to obtain because the feasible set is a non-smooth and non-convex algebraic variety. Existing techniques include projected gradient descent, fixed-rank optimization (over the maximal-rank stratum), and the LR parameterization. They all lack either global guarantees (the ability to accumulate only at critical points) or fast local convergence (e.g., if the limit has non-maximal rank). We seek optimization algorithms that enjoy both.\n  Khrulkov and Oseledets [2018] parameterize the bounded-rank variety via a desingul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14211","kind":"arxiv","version":1},"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/2406.14211/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":"2406.14211","created_at":"2026-07-05T08:34:40.481911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14211v1","created_at":"2026-07-05T08:34:40.481911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14211","created_at":"2026-07-05T08:34:40.481911+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILWN2KGJBWMD","created_at":"2026-07-05T08:34:40.481911+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILWN2KGJBWMDISRS","created_at":"2026-07-05T08:34:40.481911+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILWN2KGJ","created_at":"2026-07-05T08:34:40.481911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2503.04523","citing_title":"First-order methods on bounded-rank tensors converging to stationary points","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ","json":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ.json","graph_json":"https://pith.science/api/pith-number/ILWN2KGJBWMDISRS6BQR3ANNHJ/graph.json","events_json":"https://pith.science/api/pith-number/ILWN2KGJBWMDISRS6BQR3ANNHJ/events.json","paper":"https://pith.science/paper/ILWN2KGJ"},"agent_actions":{"view_html":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ","download_json":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ.json","view_paper":"https://pith.science/paper/ILWN2KGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14211&json=true","fetch_graph":"https://pith.science/api/pith-number/ILWN2KGJBWMDISRS6BQR3ANNHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ILWN2KGJBWMDISRS6BQR3ANNHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ/action/storage_attestation","attest_author":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ/action/author_attestation","sign_citation":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ/action/citation_signature","submit_replication":"https://pith.science/pith/ILWN2KGJBWMDISRS6BQR3ANNHJ/action/replication_record"}},"created_at":"2026-07-05T08:34:40.481911+00:00","updated_at":"2026-07-05T08:34:40.481911+00:00"}