{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2UDHOKVIH7YNK5KDU7OHKOZFSA","short_pith_number":"pith:2UDHOKVI","schema_version":"1.0","canonical_sha256":"d506772aa83ff0d57543a7dc753b25901e423e31a309da0384af894caa108530","source":{"kind":"arxiv","id":"2402.03295","version":1},"attestation_state":"computed","paper":{"title":"Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lili Mou, Yanshuai Cao, Yongchang Hao","submitted_at":"2024-02-05T18:51:17Z","abstract_excerpt":"Second-order optimization approaches like the generalized Gauss-Newton method are considered more powerful as they utilize the curvature information of the objective function with preconditioning matrices. Albeit offering tempting theoretical benefits, they are not easily applicable to modern deep learning. The major reason is due to the quadratic memory and cubic time complexity to compute the inverse of the matrix. These requirements are infeasible even with state-of-the-art hardware. In this work, we propose Ginger, an eigendecomposition for the inverse of the generalized Gauss-Newton matri"},"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":"2402.03295","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T18:51:17Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"2ff1c34529e200416738701a691f3cbe3a86c447322fc854575426217e0616a6","abstract_canon_sha256":"2b9fc02e0a1761828b6bbeae1966eb91e0d8b051f92420ea2580c539f6743cc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:33.630114Z","signature_b64":"4FGeApRhw8gpgSXe7IAEouAG4qm3wgokcGbmmg6vXjYsalNQtx2ejIrWFFBsF8HmgJYeAtwYmxE+woD1zpdhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d506772aa83ff0d57543a7dc753b25901e423e31a309da0384af894caa108530","last_reissued_at":"2026-07-05T07:41:33.629694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:33.629694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ginger: An Efficient Curvature Approximation with Linear Complexity for General Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lili Mou, Yanshuai Cao, Yongchang Hao","submitted_at":"2024-02-05T18:51:17Z","abstract_excerpt":"Second-order optimization approaches like the generalized Gauss-Newton method are considered more powerful as they utilize the curvature information of the objective function with preconditioning matrices. Albeit offering tempting theoretical benefits, they are not easily applicable to modern deep learning. The major reason is due to the quadratic memory and cubic time complexity to compute the inverse of the matrix. These requirements are infeasible even with state-of-the-art hardware. In this work, we propose Ginger, an eigendecomposition for the inverse of the generalized Gauss-Newton matri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03295","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/2402.03295/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":"2402.03295","created_at":"2026-07-05T07:41:33.629755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03295v1","created_at":"2026-07-05T07:41:33.629755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03295","created_at":"2026-07-05T07:41:33.629755+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UDHOKVIH7YN","created_at":"2026-07-05T07:41:33.629755+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UDHOKVIH7YNK5KD","created_at":"2026-07-05T07:41:33.629755+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UDHOKVI","created_at":"2026-07-05T07:41:33.629755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.19183","citing_title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA","json":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA.json","graph_json":"https://pith.science/api/pith-number/2UDHOKVIH7YNK5KDU7OHKOZFSA/graph.json","events_json":"https://pith.science/api/pith-number/2UDHOKVIH7YNK5KDU7OHKOZFSA/events.json","paper":"https://pith.science/paper/2UDHOKVI"},"agent_actions":{"view_html":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA","download_json":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA.json","view_paper":"https://pith.science/paper/2UDHOKVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03295&json=true","fetch_graph":"https://pith.science/api/pith-number/2UDHOKVIH7YNK5KDU7OHKOZFSA/graph.json","fetch_events":"https://pith.science/api/pith-number/2UDHOKVIH7YNK5KDU7OHKOZFSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA/action/storage_attestation","attest_author":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA/action/author_attestation","sign_citation":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA/action/citation_signature","submit_replication":"https://pith.science/pith/2UDHOKVIH7YNK5KDU7OHKOZFSA/action/replication_record"}},"created_at":"2026-07-05T07:41:33.629755+00:00","updated_at":"2026-07-05T07:41:33.629755+00:00"}