{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NFHPH6SR3G3KENPVPOU4OQZN7H","short_pith_number":"pith:NFHPH6SR","schema_version":"1.0","canonical_sha256":"694ef3fa51d9b6a235f57ba9c7432df9c7bf89c32a0beff4af5dadb624935383","source":{"kind":"arxiv","id":"2202.06236","version":3},"attestation_state":"computed","paper":{"title":"Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Levon Nurbekyan, Wanzhou Lei, Yunan Yang","submitted_at":"2022-02-13T07:32:17Z","abstract_excerpt":"We propose efficient numerical schemes for implementing the natural gradient descent (NGD) for a broad range of metric spaces with applications to PDE-based optimization problems. Our technique represents the natural gradient direction as a solution to a standard least-squares problem. Hence, instead of calculating, storing, or inverting the information matrix directly, we apply efficient methods from numerical linear algebra. We treat both scenarios where the Jacobian, i.e., the derivative of the state variable with respect to the parameter, is either explicitly known or implicitly given thro"},"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":"2202.06236","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-13T07:32:17Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"4b604166ae6ff3e5460dc40a7e8369653083364d551ebd21e0c70ee37077a76b","abstract_canon_sha256":"9085d7f184248a1be88818bfc25720d70c57b09bb807dfcf0ee5f7b4e9a26f10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:21.075551Z","signature_b64":"YYqOIeWRWZ+pO5dkf1AOn/yRylzqXByEV5VuVaG2pY0qpyL0SGVF1j2SzLg5vwvubMgtRfsdNuSZ5MfzOR+YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694ef3fa51d9b6a235f57ba9c7432df9c7bf89c32a0beff4af5dadb624935383","last_reissued_at":"2026-07-05T05:32:21.075064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:21.075064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Levon Nurbekyan, Wanzhou Lei, Yunan Yang","submitted_at":"2022-02-13T07:32:17Z","abstract_excerpt":"We propose efficient numerical schemes for implementing the natural gradient descent (NGD) for a broad range of metric spaces with applications to PDE-based optimization problems. Our technique represents the natural gradient direction as a solution to a standard least-squares problem. Hence, instead of calculating, storing, or inverting the information matrix directly, we apply efficient methods from numerical linear algebra. We treat both scenarios where the Jacobian, i.e., the derivative of the state variable with respect to the parameter, is either explicitly known or implicitly given thro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06236","kind":"arxiv","version":3},"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/2202.06236/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":"2202.06236","created_at":"2026-07-05T05:32:21.075127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06236v3","created_at":"2026-07-05T05:32:21.075127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06236","created_at":"2026-07-05T05:32:21.075127+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFHPH6SR3G3K","created_at":"2026-07-05T05:32:21.075127+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFHPH6SR3G3KENPV","created_at":"2026-07-05T05:32:21.075127+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFHPH6SR","created_at":"2026-07-05T05:32:21.075127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H","json":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H.json","graph_json":"https://pith.science/api/pith-number/NFHPH6SR3G3KENPVPOU4OQZN7H/graph.json","events_json":"https://pith.science/api/pith-number/NFHPH6SR3G3KENPVPOU4OQZN7H/events.json","paper":"https://pith.science/paper/NFHPH6SR"},"agent_actions":{"view_html":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H","download_json":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H.json","view_paper":"https://pith.science/paper/NFHPH6SR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06236&json=true","fetch_graph":"https://pith.science/api/pith-number/NFHPH6SR3G3KENPVPOU4OQZN7H/graph.json","fetch_events":"https://pith.science/api/pith-number/NFHPH6SR3G3KENPVPOU4OQZN7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H/action/storage_attestation","attest_author":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H/action/author_attestation","sign_citation":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H/action/citation_signature","submit_replication":"https://pith.science/pith/NFHPH6SR3G3KENPVPOU4OQZN7H/action/replication_record"}},"created_at":"2026-07-05T05:32:21.075127+00:00","updated_at":"2026-07-05T05:32:21.075127+00:00"}