{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VLPIS7LOXKQ6DYADA62CKAPQIX","short_pith_number":"pith:VLPIS7LO","schema_version":"1.0","canonical_sha256":"aade897d6ebaa1e1e00307b42501f045fbb73ab7d3ed800c872860c7c38857ef","source":{"kind":"arxiv","id":"2504.05753","version":1},"attestation_state":"computed","paper":{"title":"Accelerated Natural Gradient Method for Parametric Manifold Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Chenyi Li, Shuchen Zhu, Zaiwen Wen, Zhonglin Xie","submitted_at":"2025-04-08T07:33:04Z","abstract_excerpt":"Parametric manifold optimization problems frequently arise in various machine learning tasks, where state functions are defined on infinite-dimensional manifolds. We propose a unified accelerated natural gradient descent (ANGD) framework to address these problems. By incorporating a Hessian-driven damping term into the manifold update, we derive an accelerated Riemannian gradient (ARG) flow that mitigates oscillations. An equivalent first-order system is further presented for the ARG flow, enabling a unified discretization scheme that leads to the ANGD method. In our discrete update, our frame"},"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":"2504.05753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-04-08T07:33:04Z","cross_cats_sorted":[],"title_canon_sha256":"49254ffd4662f29ad460b3e0877b8fcfa3777472932b8c6f07f4f832f87ac771","abstract_canon_sha256":"beced6300a86e74567a9fb8dfa67a8d955a8c856b7330cb3f9ecd5dd47c4b5dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:09.097399Z","signature_b64":"3WciQdIOMcG8pLEjJFxVoSgrs7bhc+3NQ1T3fX09JR4CuWtOP6/u55+pjmJXWQMdZcleiA+LroKMMwKDMJPKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aade897d6ebaa1e1e00307b42501f045fbb73ab7d3ed800c872860c7c38857ef","last_reissued_at":"2026-07-05T10:46:09.096841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:09.096841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Natural Gradient Method for Parametric Manifold Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Chenyi Li, Shuchen Zhu, Zaiwen Wen, Zhonglin Xie","submitted_at":"2025-04-08T07:33:04Z","abstract_excerpt":"Parametric manifold optimization problems frequently arise in various machine learning tasks, where state functions are defined on infinite-dimensional manifolds. We propose a unified accelerated natural gradient descent (ANGD) framework to address these problems. By incorporating a Hessian-driven damping term into the manifold update, we derive an accelerated Riemannian gradient (ARG) flow that mitigates oscillations. An equivalent first-order system is further presented for the ARG flow, enabling a unified discretization scheme that leads to the ANGD method. In our discrete update, our frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05753","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/2504.05753/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":"2504.05753","created_at":"2026-07-05T10:46:09.096902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05753v1","created_at":"2026-07-05T10:46:09.096902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05753","created_at":"2026-07-05T10:46:09.096902+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLPIS7LOXKQ6","created_at":"2026-07-05T10:46:09.096902+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLPIS7LOXKQ6DYAD","created_at":"2026-07-05T10:46:09.096902+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLPIS7LO","created_at":"2026-07-05T10:46:09.096902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15899","citing_title":"Solving Classical and Quantum Spin Glasses with Deep Boltzmann Quantum States","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15554","citing_title":"Natural gradient descent with momentum","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX","json":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX.json","graph_json":"https://pith.science/api/pith-number/VLPIS7LOXKQ6DYADA62CKAPQIX/graph.json","events_json":"https://pith.science/api/pith-number/VLPIS7LOXKQ6DYADA62CKAPQIX/events.json","paper":"https://pith.science/paper/VLPIS7LO"},"agent_actions":{"view_html":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX","download_json":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX.json","view_paper":"https://pith.science/paper/VLPIS7LO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05753&json=true","fetch_graph":"https://pith.science/api/pith-number/VLPIS7LOXKQ6DYADA62CKAPQIX/graph.json","fetch_events":"https://pith.science/api/pith-number/VLPIS7LOXKQ6DYADA62CKAPQIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX/action/storage_attestation","attest_author":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX/action/author_attestation","sign_citation":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX/action/citation_signature","submit_replication":"https://pith.science/pith/VLPIS7LOXKQ6DYADA62CKAPQIX/action/replication_record"}},"created_at":"2026-07-05T10:46:09.096902+00:00","updated_at":"2026-07-05T10:46:09.096902+00:00"}