{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OLDVWEJXGIHSM2FIGRVD524KQU","short_pith_number":"pith:OLDVWEJX","schema_version":"1.0","canonical_sha256":"72c75b1137320f2668a8346a3eeb8a8503090c169c1f26611d8b2a7b8599a7de","source":{"kind":"arxiv","id":"2201.03962","version":4},"attestation_state":"computed","paper":{"title":"Low-rank optimization methods based on projected projected-gradient descent that accumulate at Bouligand stationary points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Guillaume Olikier, Kyle A. Gallivan, P.-A. Absil","submitted_at":"2022-01-11T14:18:54Z","abstract_excerpt":"This paper considers the problem of minimizing a differentiable function with locally Lipschitz continuous gradient on the algebraic variety of real matrices of upper-bounded rank. This problem is known to enable the formulation of various machine learning or signal processing tasks such as dimensionality reduction, collaborative filtering, and signal recovery. Several definitions of stationarity exist for this nonconvex problem. Among them, Bouligand stationarity is the strongest necessary condition for local optimality. This paper proposes two first-order methods that generate a sequence in "},"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":"2201.03962","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-01-11T14:18:54Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"7c0cf459f8464893a8d270d6340bf231463bdaba1de5dfa6fd0fb0082df973fd","abstract_canon_sha256":"d7fac7155f91ee87941ec3154ddd58b00af6735e84685b6305aaad23c1896ae5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:13:59.699341Z","signature_b64":"Bly10NgJXU34DuBvalguMBo+ppjCvhwtrsK6jdJcnjDZK6VxvDHEbW/XBfDjqTemndFE26Lf2xSDfrTcAnylDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72c75b1137320f2668a8346a3eeb8a8503090c169c1f26611d8b2a7b8599a7de","last_reissued_at":"2026-06-29T01:13:59.698821Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:13:59.698821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-rank optimization methods based on projected projected-gradient descent that accumulate at Bouligand stationary points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Guillaume Olikier, Kyle A. Gallivan, P.-A. Absil","submitted_at":"2022-01-11T14:18:54Z","abstract_excerpt":"This paper considers the problem of minimizing a differentiable function with locally Lipschitz continuous gradient on the algebraic variety of real matrices of upper-bounded rank. This problem is known to enable the formulation of various machine learning or signal processing tasks such as dimensionality reduction, collaborative filtering, and signal recovery. Several definitions of stationarity exist for this nonconvex problem. Among them, Bouligand stationarity is the strongest necessary condition for local optimality. This paper proposes two first-order methods that generate a sequence in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03962","kind":"arxiv","version":4},"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/2201.03962/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":"2201.03962","created_at":"2026-06-29T01:13:59.698895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03962v4","created_at":"2026-06-29T01:13:59.698895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03962","created_at":"2026-06-29T01:13:59.698895+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLDVWEJXGIHS","created_at":"2026-06-29T01:13:59.698895+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLDVWEJXGIHSM2FI","created_at":"2026-06-29T01:13:59.698895+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLDVWEJX","created_at":"2026-06-29T01:13:59.698895+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":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU","json":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU.json","graph_json":"https://pith.science/api/pith-number/OLDVWEJXGIHSM2FIGRVD524KQU/graph.json","events_json":"https://pith.science/api/pith-number/OLDVWEJXGIHSM2FIGRVD524KQU/events.json","paper":"https://pith.science/paper/OLDVWEJX"},"agent_actions":{"view_html":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU","download_json":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU.json","view_paper":"https://pith.science/paper/OLDVWEJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03962&json=true","fetch_graph":"https://pith.science/api/pith-number/OLDVWEJXGIHSM2FIGRVD524KQU/graph.json","fetch_events":"https://pith.science/api/pith-number/OLDVWEJXGIHSM2FIGRVD524KQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU/action/storage_attestation","attest_author":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU/action/author_attestation","sign_citation":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU/action/citation_signature","submit_replication":"https://pith.science/pith/OLDVWEJXGIHSM2FIGRVD524KQU/action/replication_record"}},"created_at":"2026-06-29T01:13:59.698895+00:00","updated_at":"2026-06-29T01:13:59.698895+00:00"}