{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:D4JZTRAEK5637B2QULDQL6AEB5","short_pith_number":"pith:D4JZTRAE","schema_version":"1.0","canonical_sha256":"1f1399c404577dbf8750a2c705f8040f4833db0a8c01b1f437976ecec34d74d4","source":{"kind":"arxiv","id":"1710.08936","version":1},"attestation_state":"computed","paper":{"title":"Curvature-aided Incremental Aggregated Gradient Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Angelia Nedic, Anna Scaglione, Hoi-To Wai, Wei Shi","submitted_at":"2017-10-24T18:12:33Z","abstract_excerpt":"We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method. Motivated by the problem of training a classifier for a d-dimensional problem, where the number of training data is $m$ and $m \\gg d \\gg 1$, the CIAG method seeks to accelerate incremental aggregated gradient (IAG) methods using aids from the curvature (or Hessian) information, while avoiding the evaluation of matrix inverses required by the incremental Newton (IN) method. Specifically, our idea is to exploit the incrementally aggregated Hessian matrix to trac"},"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":"1710.08936","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2017-10-24T18:12:33Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"ead25206fc14371e27573e6ee1d436e4f61add8c420afc3547f79b1444dfd71e","abstract_canon_sha256":"2fc5e12f2a4ef904e8cb73110b85cf69dd9a5fc9d6b4a8852427399f0bf1d26f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:00.734868Z","signature_b64":"vzoj2qitw5WLJz2L5ScYGRH3FJAtpnjPJ6mQHgf2RUjrcRjahMML3HAmCMuXvmsMYcRXCtYaG5a+s8fYJ+OIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f1399c404577dbf8750a2c705f8040f4833db0a8c01b1f437976ecec34d74d4","last_reissued_at":"2026-05-18T00:32:00.734221Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:00.734221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curvature-aided Incremental Aggregated Gradient Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Angelia Nedic, Anna Scaglione, Hoi-To Wai, Wei Shi","submitted_at":"2017-10-24T18:12:33Z","abstract_excerpt":"We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method. Motivated by the problem of training a classifier for a d-dimensional problem, where the number of training data is $m$ and $m \\gg d \\gg 1$, the CIAG method seeks to accelerate incremental aggregated gradient (IAG) methods using aids from the curvature (or Hessian) information, while avoiding the evaluation of matrix inverses required by the incremental Newton (IN) method. Specifically, our idea is to exploit the incrementally aggregated Hessian matrix to trac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.08936","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":""},"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":"1710.08936","created_at":"2026-05-18T00:32:00.734300+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.08936v1","created_at":"2026-05-18T00:32:00.734300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.08936","created_at":"2026-05-18T00:32:00.734300+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4JZTRAEK563","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4JZTRAEK5637B2Q","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4JZTRAE","created_at":"2026-05-18T12:31:10.602751+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/D4JZTRAEK5637B2QULDQL6AEB5","json":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5.json","graph_json":"https://pith.science/api/pith-number/D4JZTRAEK5637B2QULDQL6AEB5/graph.json","events_json":"https://pith.science/api/pith-number/D4JZTRAEK5637B2QULDQL6AEB5/events.json","paper":"https://pith.science/paper/D4JZTRAE"},"agent_actions":{"view_html":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5","download_json":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5.json","view_paper":"https://pith.science/paper/D4JZTRAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.08936&json=true","fetch_graph":"https://pith.science/api/pith-number/D4JZTRAEK5637B2QULDQL6AEB5/graph.json","fetch_events":"https://pith.science/api/pith-number/D4JZTRAEK5637B2QULDQL6AEB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5/action/storage_attestation","attest_author":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5/action/author_attestation","sign_citation":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5/action/citation_signature","submit_replication":"https://pith.science/pith/D4JZTRAEK5637B2QULDQL6AEB5/action/replication_record"}},"created_at":"2026-05-18T00:32:00.734300+00:00","updated_at":"2026-05-18T00:32:00.734300+00:00"}