{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GLBJRSCCGFCLUI6YKQELNZW3TA","short_pith_number":"pith:GLBJRSCC","schema_version":"1.0","canonical_sha256":"32c298c8423144ba23d85408b6e6db98140bea24196e56402030c296c43a746b","source":{"kind":"arxiv","id":"1802.03653","version":2},"attestation_state":"computed","paper":{"title":"On Symplectic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Ashia C. Wilson, Michael Betancourt, Michael I. Jordan","submitted_at":"2018-02-10T21:45:46Z","abstract_excerpt":"Accelerated gradient methods have had significant impact in machine learning -- in particular the theoretical side of machine learning -- due to their ability to achieve oracle lower bounds. But their heuristic construction has hindered their full integration into the practical machine-learning algorithmic toolbox, and has limited their scope. In this paper we build on recent work which casts acceleration as a phenomenon best explained in continuous time, and we augment that picture by providing a systematic methodology for converting continuous-time dynamics into discrete-time algorithms whil"},"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":"1802.03653","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2018-02-10T21:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"1501987aa9efd34f13a205e4ed999ddeddadd94f52a8ed0f87941423b99a1dfe","abstract_canon_sha256":"5ec515b2237c5a42fc042a5830b6254f7b700c7b18d5e73264f9879087713235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:16.176030Z","signature_b64":"ajxEaJoDRNfLrEOpQqnW/5mCUd/m02NJwBEkJPF2OJ/0dGaKLxw790E1HJx5Ez/Bh8D6K/aXcIHIkI3hx33DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32c298c8423144ba23d85408b6e6db98140bea24196e56402030c296c43a746b","last_reissued_at":"2026-05-18T00:23:16.175261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:16.175261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Symplectic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.CO","authors_text":"Ashia C. Wilson, Michael Betancourt, Michael I. Jordan","submitted_at":"2018-02-10T21:45:46Z","abstract_excerpt":"Accelerated gradient methods have had significant impact in machine learning -- in particular the theoretical side of machine learning -- due to their ability to achieve oracle lower bounds. But their heuristic construction has hindered their full integration into the practical machine-learning algorithmic toolbox, and has limited their scope. In this paper we build on recent work which casts acceleration as a phenomenon best explained in continuous time, and we augment that picture by providing a systematic methodology for converting continuous-time dynamics into discrete-time algorithms whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03653","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.03653","created_at":"2026-05-18T00:23:16.175395+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03653v2","created_at":"2026-05-18T00:23:16.175395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03653","created_at":"2026-05-18T00:23:16.175395+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLBJRSCCGFCL","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLBJRSCCGFCLUI6Y","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLBJRSCC","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11210","citing_title":"Distributed Pose Graph Optimization via Continuous Riemannian Dynamics","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06868","citing_title":"When Descent Is Too Stable: Event-Triggered Hamiltonian Learning to Optimize","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02279","citing_title":"Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA","json":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA.json","graph_json":"https://pith.science/api/pith-number/GLBJRSCCGFCLUI6YKQELNZW3TA/graph.json","events_json":"https://pith.science/api/pith-number/GLBJRSCCGFCLUI6YKQELNZW3TA/events.json","paper":"https://pith.science/paper/GLBJRSCC"},"agent_actions":{"view_html":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA","download_json":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA.json","view_paper":"https://pith.science/paper/GLBJRSCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03653&json=true","fetch_graph":"https://pith.science/api/pith-number/GLBJRSCCGFCLUI6YKQELNZW3TA/graph.json","fetch_events":"https://pith.science/api/pith-number/GLBJRSCCGFCLUI6YKQELNZW3TA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA/action/storage_attestation","attest_author":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA/action/author_attestation","sign_citation":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA/action/citation_signature","submit_replication":"https://pith.science/pith/GLBJRSCCGFCLUI6YKQELNZW3TA/action/replication_record"}},"created_at":"2026-05-18T00:23:16.175395+00:00","updated_at":"2026-05-18T00:23:16.175395+00:00"}