{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:N2HFNQTDXOGYWPEEZA7Y33SLP4","short_pith_number":"pith:N2HFNQTD","schema_version":"1.0","canonical_sha256":"6e8e56c263bb8d8b3c84c83f8dee4b7f0959ec3d18eaf5ad12d3af071e6a9c05","source":{"kind":"arxiv","id":"1808.02169","version":1},"attestation_state":"computed","paper":{"title":"Fast Variance Reduction Method with Stochastic Batch Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Xuanqing Liu","submitted_at":"2018-08-07T00:49:24Z","abstract_excerpt":"In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batch of samples to conduct a variance-reduced stochastic update. We give the linear convergence rate for this framework for composite functions, and show that the optimal strategy to achieve the optimal convergence rate per data access is to always choose batch size of 1, which is equivalent to the SAGA algorithm. However, due to the presence of cache/disk IO effect in computer architecture, the number of data access ca"},"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":"1808.02169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-07T00:49:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"af0d7b2cbb81e1dbf8248955234bf95591a2ea1478bf2da92332a1456fd783ff","abstract_canon_sha256":"7cf622c6f443d8a65f9105f6ccee0ca76c31ba58c330817c12c3ed30340f07fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:47.385026Z","signature_b64":"fQc0A+jsSKRA9HY8RIyiNhQNQOGeFyFD1Exi6wTLXQBn4j1LZvRSwMctMG1paauOYDgvbQlnSwXzprfNfKxmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e8e56c263bb8d8b3c84c83f8dee4b7f0959ec3d18eaf5ad12d3af071e6a9c05","last_reissued_at":"2026-05-18T00:08:47.384429Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:47.384429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Variance Reduction Method with Stochastic Batch Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Xuanqing Liu","submitted_at":"2018-08-07T00:49:24Z","abstract_excerpt":"In this paper we study a family of variance reduction methods with randomized batch size---at each step, the algorithm first randomly chooses the batch size and then selects a batch of samples to conduct a variance-reduced stochastic update. We give the linear convergence rate for this framework for composite functions, and show that the optimal strategy to achieve the optimal convergence rate per data access is to always choose batch size of 1, which is equivalent to the SAGA algorithm. However, due to the presence of cache/disk IO effect in computer architecture, the number of data access ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02169","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":"1808.02169","created_at":"2026-05-18T00:08:47.384511+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02169v1","created_at":"2026-05-18T00:08:47.384511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02169","created_at":"2026-05-18T00:08:47.384511+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2HFNQTDXOGY","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2HFNQTDXOGYWPEE","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2HFNQTD","created_at":"2026-05-18T12:32:40.477152+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/N2HFNQTDXOGYWPEEZA7Y33SLP4","json":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4.json","graph_json":"https://pith.science/api/pith-number/N2HFNQTDXOGYWPEEZA7Y33SLP4/graph.json","events_json":"https://pith.science/api/pith-number/N2HFNQTDXOGYWPEEZA7Y33SLP4/events.json","paper":"https://pith.science/paper/N2HFNQTD"},"agent_actions":{"view_html":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4","download_json":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4.json","view_paper":"https://pith.science/paper/N2HFNQTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02169&json=true","fetch_graph":"https://pith.science/api/pith-number/N2HFNQTDXOGYWPEEZA7Y33SLP4/graph.json","fetch_events":"https://pith.science/api/pith-number/N2HFNQTDXOGYWPEEZA7Y33SLP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4/action/storage_attestation","attest_author":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4/action/author_attestation","sign_citation":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4/action/citation_signature","submit_replication":"https://pith.science/pith/N2HFNQTDXOGYWPEEZA7Y33SLP4/action/replication_record"}},"created_at":"2026-05-18T00:08:47.384511+00:00","updated_at":"2026-05-18T00:08:47.384511+00:00"}