{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3E3T3CYFUOCO45GQNWLOYXWUQC","short_pith_number":"pith:3E3T3CYF","schema_version":"1.0","canonical_sha256":"d9373d8b05a384ee74d06d96ec5ed480bc0f5b3516a1d61cfe57b88b8a5d993c","source":{"kind":"arxiv","id":"1605.06049","version":2},"attestation_state":"computed","paper":{"title":"A Multi-Batch L-BFGS Method for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Albert S. Berahas, Jorge Nocedal, Martin Tak\\'a\\v{c}","submitted_at":"2016-05-19T16:53:50Z","abstract_excerpt":"The question of how to parallelize the stochastic gradient descent (SGD) method has received much attention in the literature. In this paper, we focus instead on batch methods that use a sizeable fraction of the training set at each iteration to facilitate parallelism, and that employ second-order information. In order to improve the learning process, we follow a multi-batch approach in which the batch changes at each iteration. This can cause difficulties because L-BFGS employs gradient differences to update the Hessian approximations, and when these gradients are computed using different dat"},"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":"1605.06049","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-05-19T16:53:50Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1d508b3d1feb4d183269afb5e46d58c331dfcd6cc4b902ca5aa31fa144213e93","abstract_canon_sha256":"9367d3ce19242539b02965c88ff07ac789beb7f4604e9148ceded642f28fa8a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:31.039034Z","signature_b64":"TGH4I4InRr8lKBEby40ffJQ2Al9dshnPNzLw5WLwTi7Sy14hdDZkSuHznqFM8nTDZ7bBc4FS/H4mm0Qt+t5YDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9373d8b05a384ee74d06d96ec5ed480bc0f5b3516a1d61cfe57b88b8a5d993c","last_reissued_at":"2026-05-18T01:01:31.038622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:31.038622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Batch L-BFGS Method for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Albert S. Berahas, Jorge Nocedal, Martin Tak\\'a\\v{c}","submitted_at":"2016-05-19T16:53:50Z","abstract_excerpt":"The question of how to parallelize the stochastic gradient descent (SGD) method has received much attention in the literature. In this paper, we focus instead on batch methods that use a sizeable fraction of the training set at each iteration to facilitate parallelism, and that employ second-order information. In order to improve the learning process, we follow a multi-batch approach in which the batch changes at each iteration. This can cause difficulties because L-BFGS employs gradient differences to update the Hessian approximations, and when these gradients are computed using different dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06049","kind":"arxiv","version":2},"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":"1605.06049","created_at":"2026-05-18T01:01:31.038684+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06049v2","created_at":"2026-05-18T01:01:31.038684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06049","created_at":"2026-05-18T01:01:31.038684+00:00"},{"alias_kind":"pith_short_12","alias_value":"3E3T3CYFUOCO","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3E3T3CYFUOCO45GQ","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3E3T3CYF","created_at":"2026-05-18T12:29:55.572404+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/3E3T3CYFUOCO45GQNWLOYXWUQC","json":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC.json","graph_json":"https://pith.science/api/pith-number/3E3T3CYFUOCO45GQNWLOYXWUQC/graph.json","events_json":"https://pith.science/api/pith-number/3E3T3CYFUOCO45GQNWLOYXWUQC/events.json","paper":"https://pith.science/paper/3E3T3CYF"},"agent_actions":{"view_html":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC","download_json":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC.json","view_paper":"https://pith.science/paper/3E3T3CYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06049&json=true","fetch_graph":"https://pith.science/api/pith-number/3E3T3CYFUOCO45GQNWLOYXWUQC/graph.json","fetch_events":"https://pith.science/api/pith-number/3E3T3CYFUOCO45GQNWLOYXWUQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC/action/storage_attestation","attest_author":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC/action/author_attestation","sign_citation":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC/action/citation_signature","submit_replication":"https://pith.science/pith/3E3T3CYFUOCO45GQNWLOYXWUQC/action/replication_record"}},"created_at":"2026-05-18T01:01:31.038684+00:00","updated_at":"2026-05-18T01:01:31.038684+00:00"}