{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WGLV5PLLUKXCR22SUZ5N4BKFQN","short_pith_number":"pith:WGLV5PLL","schema_version":"1.0","canonical_sha256":"b1975ebd6ba2ae28eb52a67ade054583785caec801da2981a493d3433977f1dc","source":{"kind":"arxiv","id":"2309.07879","version":1},"attestation_state":"computed","paper":{"title":"Acceleration by Stepsize Hedging I: Multi-Step Descent and the Silver Stepsize Schedule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Jason M. Altschuler, Pablo A. Parrilo","submitted_at":"2023-09-14T17:24:45Z","abstract_excerpt":"Can we accelerate convergence of gradient descent without changing the algorithm -- just by carefully choosing stepsizes? Surprisingly, we show that the answer is yes. Our proposed Silver Stepsize Schedule optimizes strongly convex functions in $k^{\\log_{\\rho} 2} \\approx k^{0.7864}$ iterations, where $\\rho=1+\\sqrt{2}$ is the silver ratio and $k$ is the condition number. This is intermediate between the textbook unaccelerated rate $k$ and the accelerated rate $\\sqrt{k}$ due to Nesterov in 1983. The non-strongly convex setting is conceptually identical, and standard black-box reductions imply an"},"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":"2309.07879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-09-14T17:24:45Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"033fdfcdc7e114c65ea6b8c8d52583719720327c9a08cd7b61679d3c616d2aad","abstract_canon_sha256":"25d4bbcbe7c017987c0b416a2eabbe382645bf994a76dcc8f46d87a047369c19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:57.496132Z","signature_b64":"NOY6LfbKjBbY6uFshAcHbFmVldV+DRiCDOfwW/QZWYcnPav5ZTbahUFW29apatQZbH8WphOntRYXJOpvn+uEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1975ebd6ba2ae28eb52a67ade054583785caec801da2981a493d3433977f1dc","last_reissued_at":"2026-07-05T10:40:57.495633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:57.495633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acceleration by Stepsize Hedging I: Multi-Step Descent and the Silver Stepsize Schedule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Jason M. Altschuler, Pablo A. Parrilo","submitted_at":"2023-09-14T17:24:45Z","abstract_excerpt":"Can we accelerate convergence of gradient descent without changing the algorithm -- just by carefully choosing stepsizes? Surprisingly, we show that the answer is yes. Our proposed Silver Stepsize Schedule optimizes strongly convex functions in $k^{\\log_{\\rho} 2} \\approx k^{0.7864}$ iterations, where $\\rho=1+\\sqrt{2}$ is the silver ratio and $k$ is the condition number. This is intermediate between the textbook unaccelerated rate $k$ and the accelerated rate $\\sqrt{k}$ due to Nesterov in 1983. The non-strongly convex setting is conceptually identical, and standard black-box reductions imply an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07879","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/2309.07879/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":"2309.07879","created_at":"2026-07-05T10:40:57.495694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07879v1","created_at":"2026-07-05T10:40:57.495694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07879","created_at":"2026-07-05T10:40:57.495694+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGLV5PLLUKXC","created_at":"2026-07-05T10:40:57.495694+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGLV5PLLUKXCR22S","created_at":"2026-07-05T10:40:57.495694+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGLV5PLL","created_at":"2026-07-05T10:40:57.495694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.21068","citing_title":"Finite Horizon Optimization: Framework and Applications","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN","json":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN.json","graph_json":"https://pith.science/api/pith-number/WGLV5PLLUKXCR22SUZ5N4BKFQN/graph.json","events_json":"https://pith.science/api/pith-number/WGLV5PLLUKXCR22SUZ5N4BKFQN/events.json","paper":"https://pith.science/paper/WGLV5PLL"},"agent_actions":{"view_html":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN","download_json":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN.json","view_paper":"https://pith.science/paper/WGLV5PLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07879&json=true","fetch_graph":"https://pith.science/api/pith-number/WGLV5PLLUKXCR22SUZ5N4BKFQN/graph.json","fetch_events":"https://pith.science/api/pith-number/WGLV5PLLUKXCR22SUZ5N4BKFQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN/action/storage_attestation","attest_author":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN/action/author_attestation","sign_citation":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN/action/citation_signature","submit_replication":"https://pith.science/pith/WGLV5PLLUKXCR22SUZ5N4BKFQN/action/replication_record"}},"created_at":"2026-07-05T10:40:57.495694+00:00","updated_at":"2026-07-05T10:40:57.495694+00:00"}