{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKAM7RKSFJ53TQZL7STCCPRQI3","short_pith_number":"pith:AKAM7RKS","schema_version":"1.0","canonical_sha256":"0280cfc5522a7bb9c32bfca6213e3046dcf23064802f2ecc11229a4c7092008c","source":{"kind":"arxiv","id":"2505.11670","version":1},"attestation_state":"computed","paper":{"title":"An Adaptive and Parameter-Free Nesterov's Accelerated Gradient Method for Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jaewook J. Suh, Shiqian Ma","submitted_at":"2025-05-16T20:10:03Z","abstract_excerpt":"We propose AdaNAG, an adaptive accelerated gradient method based on Nesterov's accelerated gradient method. AdaNAG is line-search-free, parameter-free, and achieves the accelerated convergence rates $f(x_k) - f_\\star = \\mathcal{O}\\left(1/k^2\\right)$ and $\\min_{i\\in\\left\\{1,\\dots, k\\right\\}} \\|\\nabla f(x_i)\\|^2 = \\mathcal{O}\\left(1/k^3\\right)$ for $L$-smooth convex function $f$. We provide a Lyapunov analysis for the convergence proof of AdaNAG, which additionally enables us to propose a novel adaptive gradient descent (GD) method, AdaGD. AdaGD achieves the non-ergodic convergence rate $f(x_k) "},"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":"2505.11670","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-05-16T20:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"f32e23a4d8eb5f9eda42affccce130c8d16a40f20253aca1fd5c342d9f207cc5","abstract_canon_sha256":"8e2c1310e4787f4437962dc8094d5c5f052b9766226119ec2e891d5b7ed4a5a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:25.171328Z","signature_b64":"zk9u+0lXDH9YyQJFAaZuu0qx4qgsCd62zXULPd6uj1yX0Qt5gyWBH01PFGCcsgt86WVf2/hV0ccHYU3qDtMsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0280cfc5522a7bb9c32bfca6213e3046dcf23064802f2ecc11229a4c7092008c","last_reissued_at":"2026-07-05T11:04:25.170828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:25.170828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Adaptive and Parameter-Free Nesterov's Accelerated Gradient Method for Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Jaewook J. Suh, Shiqian Ma","submitted_at":"2025-05-16T20:10:03Z","abstract_excerpt":"We propose AdaNAG, an adaptive accelerated gradient method based on Nesterov's accelerated gradient method. AdaNAG is line-search-free, parameter-free, and achieves the accelerated convergence rates $f(x_k) - f_\\star = \\mathcal{O}\\left(1/k^2\\right)$ and $\\min_{i\\in\\left\\{1,\\dots, k\\right\\}} \\|\\nabla f(x_i)\\|^2 = \\mathcal{O}\\left(1/k^3\\right)$ for $L$-smooth convex function $f$. We provide a Lyapunov analysis for the convergence proof of AdaNAG, which additionally enables us to propose a novel adaptive gradient descent (GD) method, AdaGD. AdaGD achieves the non-ergodic convergence rate $f(x_k) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11670","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/2505.11670/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":"2505.11670","created_at":"2026-07-05T11:04:25.170894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11670v1","created_at":"2026-07-05T11:04:25.170894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11670","created_at":"2026-07-05T11:04:25.170894+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKAM7RKSFJ53","created_at":"2026-07-05T11:04:25.170894+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKAM7RKSFJ53TQZL","created_at":"2026-07-05T11:04:25.170894+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKAM7RKS","created_at":"2026-07-05T11:04:25.170894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15512","citing_title":"Auto-Conditioned Frank-Wolfe Algorithms","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23492","citing_title":"Universal and Parameter-free Gradient Sliding for Composite Optimization","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15512","citing_title":"Auto-Conditioned Frank-Wolfe Algorithms","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06525","citing_title":"Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3","json":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3.json","graph_json":"https://pith.science/api/pith-number/AKAM7RKSFJ53TQZL7STCCPRQI3/graph.json","events_json":"https://pith.science/api/pith-number/AKAM7RKSFJ53TQZL7STCCPRQI3/events.json","paper":"https://pith.science/paper/AKAM7RKS"},"agent_actions":{"view_html":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3","download_json":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3.json","view_paper":"https://pith.science/paper/AKAM7RKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11670&json=true","fetch_graph":"https://pith.science/api/pith-number/AKAM7RKSFJ53TQZL7STCCPRQI3/graph.json","fetch_events":"https://pith.science/api/pith-number/AKAM7RKSFJ53TQZL7STCCPRQI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3/action/storage_attestation","attest_author":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3/action/author_attestation","sign_citation":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3/action/citation_signature","submit_replication":"https://pith.science/pith/AKAM7RKSFJ53TQZL7STCCPRQI3/action/replication_record"}},"created_at":"2026-07-05T11:04:25.170894+00:00","updated_at":"2026-07-05T11:04:25.170894+00:00"}