{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BFZZN2HVM6J53QNDRRCZGFACDK","short_pith_number":"pith:BFZZN2HV","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"},"canonical_sha256":"097396e8f56793ddc1a38c459314021a8ec767e26226bb508b645f454207b483","source":{"kind":"arxiv","id":"1704.04966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04966","created_at":"2026-05-18T00:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04966v1","created_at":"2026-05-18T00:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04966","created_at":"2026-05-18T00:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"BFZZN2HVM6J5","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BFZZN2HVM6J53QND","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BFZZN2HV","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BFZZN2HVM6J53QNDRRCZGFACDK","target":"record","payload":{"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"},"canonical_sha256":"097396e8f56793ddc1a38c459314021a8ec767e26226bb508b645f454207b483","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"},"source_kind":"arxiv","source_id":"1704.04966","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JTHIbfCWdDRTkD8gxlRy8ltq3oPqV1//TaJzoIJdvsHO0ijhQrcH3DyDr5KBumjLAOorCIuBCl8t2gJrkMDiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:49:05.526838Z"},"content_sha256":"9aaa3013aafdf02fb16978b8438641e17bf3e2c1e2c934dd7c9fc23b7c087d48","schema_version":"1.0","event_id":"sha256:9aaa3013aafdf02fb16978b8438641e17bf3e2c1e2c934dd7c9fc23b7c087d48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BFZZN2HVM6J53QNDRRCZGFACDK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lagfPxQ7VgS+xQqWjuIqSGBrN3OeQtmfP5caOHjC77K0ROcg2yVMHjkXzT8UeO1nawJpmNDRXKQmphm3KgWYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:49:05.527194Z"},"content_sha256":"155de9d1aa71067eb327879fbe402499d9f742c177829500cc2551caa28a6dbc","schema_version":"1.0","event_id":"sha256:155de9d1aa71067eb327879fbe402499d9f742c177829500cc2551caa28a6dbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/bundle.json","state_url":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFZZN2HVM6J53QNDRRCZGFACDK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T22:49:05Z","links":{"resolver":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK","bundle":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/bundle.json","state":"https://pith.science/pith/BFZZN2HVM6J53QNDRRCZGFACDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFZZN2HVM6J53QNDRRCZGFACDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BFZZN2HVM6J53QNDRRCZGFACDK","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":"468970b08eabe2f538e1b2bd5214cd52f5056bc84048448a78636ea76e90e192","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T13:50:43Z","title_canon_sha256":"940ef862c03d814b62d5e7a10fbc96ccfb2ae7ebc618816e8bd29b1d32745c4a"},"schema_version":"1.0","source":{"id":"1704.04966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.04966","created_at":"2026-05-18T00:46:17Z"},{"alias_kind":"arxiv_version","alias_value":"1704.04966v1","created_at":"2026-05-18T00:46:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04966","created_at":"2026-05-18T00:46:17Z"},{"alias_kind":"pith_short_12","alias_value":"BFZZN2HVM6J5","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BFZZN2HVM6J53QND","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BFZZN2HV","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:155de9d1aa71067eb327879fbe402499d9f742c177829500cc2551caa28a6dbc","target":"graph","created_at":"2026-05-18T00:46:17Z","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"},"paper":{"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","authors_text":"Fanhua Shang","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T13:50:43Z","title":"Larger is Better: The Effect of Learning Rates Enjoyed by Stochastic Optimization with Progressive Variance Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04966","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":"sha256:9aaa3013aafdf02fb16978b8438641e17bf3e2c1e2c934dd7c9fc23b7c087d48","target":"record","created_at":"2026-05-18T00:46:17Z","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":"468970b08eabe2f538e1b2bd5214cd52f5056bc84048448a78636ea76e90e192","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T13:50:43Z","title_canon_sha256":"940ef862c03d814b62d5e7a10fbc96ccfb2ae7ebc618816e8bd29b1d32745c4a"},"schema_version":"1.0","source":{"id":"1704.04966","kind":"arxiv","version":1}},"canonical_sha256":"097396e8f56793ddc1a38c459314021a8ec767e26226bb508b645f454207b483","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"097396e8f56793ddc1a38c459314021a8ec767e26226bb508b645f454207b483","first_computed_at":"2026-05-18T00:46:17.348621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:17.348621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ugkkn61dRsEbnTg6HEv20J46Dh9DScyMzwE5QmG+KbKvMiZICo8B6e9j83rPOm7JxIAcSxEyColtrdSnaCeFBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:17.349243Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.04966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9aaa3013aafdf02fb16978b8438641e17bf3e2c1e2c934dd7c9fc23b7c087d48","sha256:155de9d1aa71067eb327879fbe402499d9f742c177829500cc2551caa28a6dbc"],"state_sha256":"9596560ccec81b1d6e1769d543622b128d1828c2feae28370cf8c4d71cd46f5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bsKTXe0+PCoWQiafR0ZGSiTg0GVE61UmqM9TKt7PbPfVD7mUsPRw+qhQJUCluVWUa8ZcbOaxh0M7tyohjg4eBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:49:05.529193Z","bundle_sha256":"21f2109ad4ec2595c3e70492a7d28e018decfd5d236dfaa0ff6d62816c4ed628"}}