{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DYSD2BXXIIYLCIJNMPX3R256ST","short_pith_number":"pith:DYSD2BXX","schema_version":"1.0","canonical_sha256":"1e243d06f74230b1212d63efb8ebbe94f651a790525ea82e820bb12cb6f7a176","source":{"kind":"arxiv","id":"2212.08769","version":1},"attestation_state":"computed","paper":{"title":"Improving Levenberg-Marquardt Algorithm for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Omead Pooladzandi, Yiming Zhou","submitted_at":"2022-12-17T00:36:46Z","abstract_excerpt":"We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks. We compare the performance of the LM method with other popular first-order algorithms such as SGD and Adam, as well as other second-order algorithms such as L-BFGS , Hessian-Free and KFAC. We further speed up the LM method by using adaptive momentum, learning rate line search, and uphill step acceptance."},"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":"2212.08769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-17T00:36:46Z","cross_cats_sorted":[],"title_canon_sha256":"9df57ae2d71792a55c55ff58a7ad302f2f1f98d76f4507cdfeb441f55c44c8f0","abstract_canon_sha256":"d08818ae6293e0b62a37633eb1b3c80bab305c8263ea6dcdf0e91cd9a6392c8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:14.157426Z","signature_b64":"qcipJUtJDib3Hrs1JSctJPgyM/Z/3bO0hvAAfFtEqVDNx/AK4rxtmNYsc2IkH9ixDCiXLtU1tlobtu6n3Ci8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e243d06f74230b1212d63efb8ebbe94f651a790525ea82e820bb12cb6f7a176","last_reissued_at":"2026-07-05T05:26:14.157025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:14.157025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Levenberg-Marquardt Algorithm for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Omead Pooladzandi, Yiming Zhou","submitted_at":"2022-12-17T00:36:46Z","abstract_excerpt":"We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks. We compare the performance of the LM method with other popular first-order algorithms such as SGD and Adam, as well as other second-order algorithms such as L-BFGS , Hessian-Free and KFAC. We further speed up the LM method by using adaptive momentum, learning rate line search, and uphill step acceptance."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08769","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/2212.08769/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":"2212.08769","created_at":"2026-07-05T05:26:14.157085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08769v1","created_at":"2026-07-05T05:26:14.157085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08769","created_at":"2026-07-05T05:26:14.157085+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYSD2BXXIIYL","created_at":"2026-07-05T05:26:14.157085+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYSD2BXXIIYLCIJN","created_at":"2026-07-05T05:26:14.157085+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYSD2BXX","created_at":"2026-07-05T05:26:14.157085+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/DYSD2BXXIIYLCIJNMPX3R256ST","json":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST.json","graph_json":"https://pith.science/api/pith-number/DYSD2BXXIIYLCIJNMPX3R256ST/graph.json","events_json":"https://pith.science/api/pith-number/DYSD2BXXIIYLCIJNMPX3R256ST/events.json","paper":"https://pith.science/paper/DYSD2BXX"},"agent_actions":{"view_html":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST","download_json":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST.json","view_paper":"https://pith.science/paper/DYSD2BXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08769&json=true","fetch_graph":"https://pith.science/api/pith-number/DYSD2BXXIIYLCIJNMPX3R256ST/graph.json","fetch_events":"https://pith.science/api/pith-number/DYSD2BXXIIYLCIJNMPX3R256ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST/action/storage_attestation","attest_author":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST/action/author_attestation","sign_citation":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST/action/citation_signature","submit_replication":"https://pith.science/pith/DYSD2BXXIIYLCIJNMPX3R256ST/action/replication_record"}},"created_at":"2026-07-05T05:26:14.157085+00:00","updated_at":"2026-07-05T05:26:14.157085+00:00"}