{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFPAKPUH7QYJKU4TVELMSCYFHF","short_pith_number":"pith:RFPAKPUH","schema_version":"1.0","canonical_sha256":"895e053e87fc30955393a916c90b0539403973699e40a15508bb7fb0af58aa48","source":{"kind":"arxiv","id":"2405.16020","version":1},"attestation_state":"computed","paper":{"title":"Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Liangzu Peng, Wotao Yin","submitted_at":"2024-05-25T02:50:41Z","abstract_excerpt":"Block coordinate descent is a powerful algorithmic template suitable for big data optimization. This template admits a lot of variants including block gradient descent (BGD), which performs gradient descent on a selected block of variables, while keeping other variables fixed. For a very long time, the stepsize for each block has tacitly been set to one divided by the block-wise Lipschitz smoothness constant, imitating the vanilla stepsize rule for gradient descent (GD). However, such a choice for BGD has not yet been able to theoretically justify its empirical superiority over GD, as existing"},"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":"2405.16020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-05-25T02:50:41Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"9710e6624b6a8d728acb53080f0dc610261e424112860de68a034530b4398952","abstract_canon_sha256":"8de18394ba17ec42776ac79fc39eff28ec64bb66be2d231757692c5f08512411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:00.656068Z","signature_b64":"IRRWXLPUGotcy1k6hwn49NrkC6KZeMCpODRp2yd+smMhUIssHKIl4XVJiB3PJOH7OpQFCzhjUiU5DBne6d/RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"895e053e87fc30955393a916c90b0539403973699e40a15508bb7fb0af58aa48","last_reissued_at":"2026-07-05T08:23:00.655437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:00.655437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Liangzu Peng, Wotao Yin","submitted_at":"2024-05-25T02:50:41Z","abstract_excerpt":"Block coordinate descent is a powerful algorithmic template suitable for big data optimization. This template admits a lot of variants including block gradient descent (BGD), which performs gradient descent on a selected block of variables, while keeping other variables fixed. For a very long time, the stepsize for each block has tacitly been set to one divided by the block-wise Lipschitz smoothness constant, imitating the vanilla stepsize rule for gradient descent (GD). However, such a choice for BGD has not yet been able to theoretically justify its empirical superiority over GD, as existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16020","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/2405.16020/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":"2405.16020","created_at":"2026-07-05T08:23:00.655526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16020v1","created_at":"2026-07-05T08:23:00.655526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16020","created_at":"2026-07-05T08:23:00.655526+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFPAKPUH7QYJ","created_at":"2026-07-05T08:23:00.655526+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFPAKPUH7QYJKU4T","created_at":"2026-07-05T08:23:00.655526+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFPAKPUH","created_at":"2026-07-05T08:23:00.655526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14080","citing_title":"A Unified Blockwise Measurement Design for Learning Quantum Channels and Lindbladians via Low-Rank Matrix Sensing","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF","json":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF.json","graph_json":"https://pith.science/api/pith-number/RFPAKPUH7QYJKU4TVELMSCYFHF/graph.json","events_json":"https://pith.science/api/pith-number/RFPAKPUH7QYJKU4TVELMSCYFHF/events.json","paper":"https://pith.science/paper/RFPAKPUH"},"agent_actions":{"view_html":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF","download_json":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF.json","view_paper":"https://pith.science/paper/RFPAKPUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16020&json=true","fetch_graph":"https://pith.science/api/pith-number/RFPAKPUH7QYJKU4TVELMSCYFHF/graph.json","fetch_events":"https://pith.science/api/pith-number/RFPAKPUH7QYJKU4TVELMSCYFHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF/action/storage_attestation","attest_author":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF/action/author_attestation","sign_citation":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF/action/citation_signature","submit_replication":"https://pith.science/pith/RFPAKPUH7QYJKU4TVELMSCYFHF/action/replication_record"}},"created_at":"2026-07-05T08:23:00.655526+00:00","updated_at":"2026-07-05T08:23:00.655526+00:00"}