{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JL4FJRL5ZEAAXN5JZRWV4VNJXV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3c3b0934ec1b57a966a190ca3bd1c3cb7bbbf0ee61b573d298748f3d6db8b37","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T03:51:38Z","title_canon_sha256":"de5cfd250681aa96b04ed95a6b9e5a8a8d6bcf859baaf86572930f5c3a2a0cb0"},"schema_version":"1.0","source":{"id":"2308.02123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02123","created_at":"2026-07-05T06:37:38Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02123v1","created_at":"2026-07-05T06:37:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02123","created_at":"2026-07-05T06:37:38Z"},{"alias_kind":"pith_short_12","alias_value":"JL4FJRL5ZEAA","created_at":"2026-07-05T06:37:38Z"},{"alias_kind":"pith_short_16","alias_value":"JL4FJRL5ZEAAXN5J","created_at":"2026-07-05T06:37:38Z"},{"alias_kind":"pith_short_8","alias_value":"JL4FJRL5","created_at":"2026-07-05T06:37:38Z"}],"graph_snapshots":[{"event_id":"sha256:bd3a6c8023f5c3b165d091362e7b5748984afeb50429f24d7237ad658210de21","target":"graph","created_at":"2026-07-05T06:37:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.02123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Li, Lin Zhang, Shaohuai Shi","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T03:51:38Z","title":"Eva: A General Vectorized Approximation Framework for Second-order Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02123","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c032f1d903a4bc6e81c8956501623459ab075bb0c8a3b5073bd9e20eab70c951","target":"record","created_at":"2026-07-05T06:37:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3c3b0934ec1b57a966a190ca3bd1c3cb7bbbf0ee61b573d298748f3d6db8b37","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T03:51:38Z","title_canon_sha256":"de5cfd250681aa96b04ed95a6b9e5a8a8d6bcf859baaf86572930f5c3a2a0cb0"},"schema_version":"1.0","source":{"id":"2308.02123","kind":"arxiv","version":1}},"canonical_sha256":"4af854c57dc9000bb7a9cc6d5e55a9bd5f56847cbd6848ebd20204ecd10b3acd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4af854c57dc9000bb7a9cc6d5e55a9bd5f56847cbd6848ebd20204ecd10b3acd","first_computed_at":"2026-07-05T06:37:38.030801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:38.030801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WrTthLeo9KO5ZY/miw2e/TGQyh6djI+6vQa9Ka7bAjFa1tNnEyWJ9ALnCsCML42ULaLUKPcXxn7I9RUXY0FdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:38.031243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.02123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c032f1d903a4bc6e81c8956501623459ab075bb0c8a3b5073bd9e20eab70c951","sha256:bd3a6c8023f5c3b165d091362e7b5748984afeb50429f24d7237ad658210de21"],"state_sha256":"1f9da464eda067f23621041f3b82f3d7e424d5deee10157dc61803a05aeb92cb"}