{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BFZZN2HVM6J53QNDRRCZGFACDK","short_pith_number":"pith:BFZZN2HV","schema_version":"1.0","canonical_sha256":"097396e8f56793ddc1a38c459314021a8ec767e26226bb508b645f454207b483","source":{"kind":"arxiv","id":"1704.04966","version":1},"attestation_state":"computed","paper":{"title":"Larger is Better: The Effect of Learning Rates Enjoyed by Stochastic Optimization with Progressive Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fanhua Shang","submitted_at":"2017-04-17T13:50:43Z","abstract_excerpt":"In this paper, we propose a simple variant of the original stochastic variance reduction gradient (SVRG), where hereafter we refer to as the variance reduced stochastic gradient descent (VR-SGD). Different from the choices of the snapshot point and starting point in SVRG and its proximal variant, Prox-SVRG, the two vectors of each epoch in VR-SGD are set to the average and last iterate of the previous epoch, respectively. This setting allows us to use much larger learning rates or step sizes than SVRG, e.g., 3/(7L) for VR-SGD vs 1/(10L) for SVRG, and also makes our convergence analysis more ch"},"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":"1704.04966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T13:50:43Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"940ef862c03d814b62d5e7a10fbc96ccfb2ae7ebc618816e8bd29b1d32745c4a","abstract_canon_sha256":"468970b08eabe2f538e1b2bd5214cd52f5056bc84048448a78636ea76e90e192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:17.349243Z","signature_b64":"Ugkkn61dRsEbnTg6HEv20J46Dh9DScyMzwE5QmG+KbKvMiZICo8B6e9j83rPOm7JxIAcSxEyColtrdSnaCeFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"097396e8f56793ddc1a38c459314021a8ec767e26226bb508b645f454207b483","last_reissued_at":"2026-05-18T00:46:17.348621Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:17.348621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Larger is Better: The Effect of Learning Rates Enjoyed by Stochastic Optimization with Progressive Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fanhua Shang","submitted_at":"2017-04-17T13:50:43Z","abstract_excerpt":"In this paper, we propose a simple variant of the original stochastic variance reduction gradient (SVRG), where hereafter we refer to as the variance reduced stochastic gradient descent (VR-SGD). Different from the choices of the snapshot point and starting point in SVRG and its proximal variant, Prox-SVRG, the two vectors of each epoch in VR-SGD are set to the average and last iterate of the previous epoch, respectively. This setting allows us to use much larger learning rates or step sizes than SVRG, e.g., 3/(7L) for VR-SGD vs 1/(10L) for SVRG, and also makes our convergence analysis more ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04966","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":"1704.04966","created_at":"2026-05-18T00:46:17.348706+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04966v1","created_at":"2026-05-18T00:46:17.348706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04966","created_at":"2026-05-18T00:46:17.348706+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFZZN2HVM6J5","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFZZN2HVM6J53QND","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFZZN2HV","created_at":"2026-05-18T12:31:08.081275+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/BFZZN2HVM6J53QNDRRCZGFACDK","json":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK.json","graph_json":"https://pith.science/api/pith-number/BFZZN2HVM6J53QNDRRCZGFACDK/graph.json","events_json":"https://pith.science/api/pith-number/BFZZN2HVM6J53QNDRRCZGFACDK/events.json","paper":"https://pith.science/paper/BFZZN2HV"},"agent_actions":{"view_html":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK","download_json":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK.json","view_paper":"https://pith.science/paper/BFZZN2HV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04966&json=true","fetch_graph":"https://pith.science/api/pith-number/BFZZN2HVM6J53QNDRRCZGFACDK/graph.json","fetch_events":"https://pith.science/api/pith-number/BFZZN2HVM6J53QNDRRCZGFACDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/action/storage_attestation","attest_author":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/action/author_attestation","sign_citation":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/action/citation_signature","submit_replication":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/action/replication_record"}},"created_at":"2026-05-18T00:46:17.348706+00:00","updated_at":"2026-05-18T00:46:17.348706+00:00"}