{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JL4FJRL5ZEAAXN5JZRWV4VNJXV","short_pith_number":"pith:JL4FJRL5","schema_version":"1.0","canonical_sha256":"4af854c57dc9000bb7a9cc6d5e55a9bd5f56847cbd6848ebd20204ecd10b3acd","source":{"kind":"arxiv","id":"2308.02123","version":1},"attestation_state":"computed","paper":{"title":"Eva: A General Vectorized Approximation Framework for Second-order Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Li, Lin Zhang, Shaohuai Shi","submitted_at":"2023-08-04T03:51:38Z","abstract_excerpt":"Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order counterparts such as stochastic gradient descent (SGD). In this work, we present a memory- and time-efficient second-order algorithm named Eva with two novel techniques: 1) we construct the second-order information with the Kronecker factorization of small stochastic vectors over a mini-batch of training data to reduce memory consumption, and 2) we derive a"},"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":"2308.02123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T03:51:38Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"de5cfd250681aa96b04ed95a6b9e5a8a8d6bcf859baaf86572930f5c3a2a0cb0","abstract_canon_sha256":"b3c3b0934ec1b57a966a190ca3bd1c3cb7bbbf0ee61b573d298748f3d6db8b37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:38.031243Z","signature_b64":"WrTthLeo9KO5ZY/miw2e/TGQyh6djI+6vQa9Ka7bAjFa1tNnEyWJ9ALnCsCML42ULaLUKPcXxn7I9RUXY0FdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4af854c57dc9000bb7a9cc6d5e55a9bd5f56847cbd6848ebd20204ecd10b3acd","last_reissued_at":"2026-07-05T06:37:38.030801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:38.030801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eva: A General Vectorized Approximation Framework for Second-order Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bo Li, Lin Zhang, Shaohuai Shi","submitted_at":"2023-08-04T03:51:38Z","abstract_excerpt":"Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order counterparts such as stochastic gradient descent (SGD). In this work, we present a memory- and time-efficient second-order algorithm named Eva with two novel techniques: 1) we construct the second-order information with the Kronecker factorization of small stochastic vectors over a mini-batch of training data to reduce memory consumption, and 2) we derive a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02123","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/2308.02123/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":"2308.02123","created_at":"2026-07-05T06:37:38.030854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02123v1","created_at":"2026-07-05T06:37:38.030854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02123","created_at":"2026-07-05T06:37:38.030854+00:00"},{"alias_kind":"pith_short_12","alias_value":"JL4FJRL5ZEAA","created_at":"2026-07-05T06:37:38.030854+00:00"},{"alias_kind":"pith_short_16","alias_value":"JL4FJRL5ZEAAXN5J","created_at":"2026-07-05T06:37:38.030854+00:00"},{"alias_kind":"pith_short_8","alias_value":"JL4FJRL5","created_at":"2026-07-05T06:37:38.030854+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/JL4FJRL5ZEAAXN5JZRWV4VNJXV","json":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV.json","graph_json":"https://pith.science/api/pith-number/JL4FJRL5ZEAAXN5JZRWV4VNJXV/graph.json","events_json":"https://pith.science/api/pith-number/JL4FJRL5ZEAAXN5JZRWV4VNJXV/events.json","paper":"https://pith.science/paper/JL4FJRL5"},"agent_actions":{"view_html":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV","download_json":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV.json","view_paper":"https://pith.science/paper/JL4FJRL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02123&json=true","fetch_graph":"https://pith.science/api/pith-number/JL4FJRL5ZEAAXN5JZRWV4VNJXV/graph.json","fetch_events":"https://pith.science/api/pith-number/JL4FJRL5ZEAAXN5JZRWV4VNJXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV/action/storage_attestation","attest_author":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV/action/author_attestation","sign_citation":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV/action/citation_signature","submit_replication":"https://pith.science/pith/JL4FJRL5ZEAAXN5JZRWV4VNJXV/action/replication_record"}},"created_at":"2026-07-05T06:37:38.030854+00:00","updated_at":"2026-07-05T06:37:38.030854+00:00"}