{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VBX2X6JCRN63F6VTHUKMBAWHYB","short_pith_number":"pith:VBX2X6JC","schema_version":"1.0","canonical_sha256":"a86fabf9228b7db2fab33d14c082c7c0632a6986eb38b98ed20fcb517e1c83f5","source":{"kind":"arxiv","id":"2305.14744","version":3},"attestation_state":"computed","paper":{"title":"Block Coordinate Descent on Smooth Manifolds: Convergence Theory and Twenty-One Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Liangzu Peng, Ren\\'e Vidal","submitted_at":"2023-05-24T05:32:49Z","abstract_excerpt":"Block coordinate descent is an optimization paradigm that iteratively updates one block of variables at a time, making it quite amenable to big data applications due to its scalability and performance. Its convergence behavior has been extensively studied in the (block-wise) convex case, but it is much less explored in the non-convex case. In this paper we analyze the convergence of block coordinate methods on non-convex sets and derive convergence rates on smooth manifolds under natural or weaker assumptions than prior work. Our analysis applies to many non-convex problems, including ones tha"},"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":"2305.14744","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-05-24T05:32:49Z","cross_cats_sorted":[],"title_canon_sha256":"34b05ce9c55aefa56cd8ee974ac53ae1cc8a1b4fb2f1950b7065182d9e9572be","abstract_canon_sha256":"8ac36adcb8c63295205b1bc78cda58870de5840112850e1ae3059e5dacb34cd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:52.473782Z","signature_b64":"fXVCa7sOkrdLRUzFFdyDibSHOKd00V1DfrDLvhewxTOAnFdvtLJxlTaDjbUAKSZ0Ux3d58VFF90wKjSqdCGMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a86fabf9228b7db2fab33d14c082c7c0632a6986eb38b98ed20fcb517e1c83f5","last_reissued_at":"2026-07-05T06:59:52.473305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:52.473305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Block Coordinate Descent on Smooth Manifolds: Convergence Theory and Twenty-One Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Liangzu Peng, Ren\\'e Vidal","submitted_at":"2023-05-24T05:32:49Z","abstract_excerpt":"Block coordinate descent is an optimization paradigm that iteratively updates one block of variables at a time, making it quite amenable to big data applications due to its scalability and performance. Its convergence behavior has been extensively studied in the (block-wise) convex case, but it is much less explored in the non-convex case. In this paper we analyze the convergence of block coordinate methods on non-convex sets and derive convergence rates on smooth manifolds under natural or weaker assumptions than prior work. Our analysis applies to many non-convex problems, including ones tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14744","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.14744/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":"2305.14744","created_at":"2026-07-05T06:59:52.473369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14744v3","created_at":"2026-07-05T06:59:52.473369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14744","created_at":"2026-07-05T06:59:52.473369+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBX2X6JCRN63","created_at":"2026-07-05T06:59:52.473369+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBX2X6JCRN63F6VT","created_at":"2026-07-05T06:59:52.473369+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBX2X6JC","created_at":"2026-07-05T06:59:52.473369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27455","citing_title":"Directed Graph Topology Inference via Graph Filter Identification","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB","json":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB.json","graph_json":"https://pith.science/api/pith-number/VBX2X6JCRN63F6VTHUKMBAWHYB/graph.json","events_json":"https://pith.science/api/pith-number/VBX2X6JCRN63F6VTHUKMBAWHYB/events.json","paper":"https://pith.science/paper/VBX2X6JC"},"agent_actions":{"view_html":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB","download_json":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB.json","view_paper":"https://pith.science/paper/VBX2X6JC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14744&json=true","fetch_graph":"https://pith.science/api/pith-number/VBX2X6JCRN63F6VTHUKMBAWHYB/graph.json","fetch_events":"https://pith.science/api/pith-number/VBX2X6JCRN63F6VTHUKMBAWHYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB/action/storage_attestation","attest_author":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB/action/author_attestation","sign_citation":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB/action/citation_signature","submit_replication":"https://pith.science/pith/VBX2X6JCRN63F6VTHUKMBAWHYB/action/replication_record"}},"created_at":"2026-07-05T06:59:52.473369+00:00","updated_at":"2026-07-05T06:59:52.473369+00:00"}