{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WYR7XWJFGAMHXJV4RIQ2E6E7MU","short_pith_number":"pith:WYR7XWJF","schema_version":"1.0","canonical_sha256":"b623fbd92530187ba6bc8a21a2789f651671e054d5bb05e4dacea07d2c348249","source":{"kind":"arxiv","id":"1603.04245","version":1},"attestation_state":"computed","paper":{"title":"A Variational Perspective on Accelerated Methods in Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Andre Wibisono, Ashia C. Wilson, Michael I. Jordan","submitted_at":"2016-03-14T13:00:18Z","abstract_excerpt":"Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural scope of the acceleration concept. In this paper, we study accelerated methods from a continuous-time perspective. We show that there is a Lagrangian functional that we call the \\emph{Bregman Lagrangian} which generates a large class of accelerated methods in continuous time, including (but not limited to) accelerated gradient descent, its non-E"},"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":"1603.04245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-03-14T13:00:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"455680589ee0af4db23b91236b2cea0a38028fb1f956900d2798a3ecf3d13252","abstract_canon_sha256":"4e3bf9eff63a1123c6f5a11cfe836109c6771f61c1a6e4a30aeda5962895472e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:47.709840Z","signature_b64":"R+oYXllQzJ+bq34xmeQXmYGRFeuvqmP8jhfmss4CPMMpU7V4mriGxU2LmfjIgvoXz7YJU62snRzZk8dI9QZRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b623fbd92530187ba6bc8a21a2789f651671e054d5bb05e4dacea07d2c348249","last_reissued_at":"2026-07-05T04:29:47.709472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:47.709472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variational Perspective on Accelerated Methods in Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Andre Wibisono, Ashia C. Wilson, Michael I. Jordan","submitted_at":"2016-03-14T13:00:18Z","abstract_excerpt":"Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural scope of the acceleration concept. In this paper, we study accelerated methods from a continuous-time perspective. We show that there is a Lagrangian functional that we call the \\emph{Bregman Lagrangian} which generates a large class of accelerated methods in continuous time, including (but not limited to) accelerated gradient descent, its non-E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.04245","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/1603.04245/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":"1603.04245","created_at":"2026-07-05T04:29:47.709533+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.04245v1","created_at":"2026-07-05T04:29:47.709533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.04245","created_at":"2026-07-05T04:29:47.709533+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYR7XWJFGAMH","created_at":"2026-07-05T04:29:47.709533+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYR7XWJFGAMHXJV4","created_at":"2026-07-05T04:29:47.709533+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYR7XWJF","created_at":"2026-07-05T04:29:47.709533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.06723","citing_title":"Optimization Geometrodynamics: Variational Reduction and Interaction Curvature","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07204","citing_title":"Restricted Dynamic Geometric Complexity: Path-Space Reduction and M\\\"obius--Jacobi Response","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07206","citing_title":"Causal Optimizer Interaction Calculus: Hidden Geometric Relaxation and Identifiable Interventions","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19050","citing_title":"First-Order Methods for Solving Convex (Strongly) Concave Minimax Problems with Functional Constraints","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14108","citing_title":"Momentum Further Constrains Sharpness at the Edge of Stochastic Stability","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU","json":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU.json","graph_json":"https://pith.science/api/pith-number/WYR7XWJFGAMHXJV4RIQ2E6E7MU/graph.json","events_json":"https://pith.science/api/pith-number/WYR7XWJFGAMHXJV4RIQ2E6E7MU/events.json","paper":"https://pith.science/paper/WYR7XWJF"},"agent_actions":{"view_html":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU","download_json":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU.json","view_paper":"https://pith.science/paper/WYR7XWJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.04245&json=true","fetch_graph":"https://pith.science/api/pith-number/WYR7XWJFGAMHXJV4RIQ2E6E7MU/graph.json","fetch_events":"https://pith.science/api/pith-number/WYR7XWJFGAMHXJV4RIQ2E6E7MU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU/action/storage_attestation","attest_author":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU/action/author_attestation","sign_citation":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU/action/citation_signature","submit_replication":"https://pith.science/pith/WYR7XWJFGAMHXJV4RIQ2E6E7MU/action/replication_record"}},"created_at":"2026-07-05T04:29:47.709533+00:00","updated_at":"2026-07-05T04:29:47.709533+00:00"}