{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RIRAI3GP6VUDW73RN3M6AXIZBV","short_pith_number":"pith:RIRAI3GP","canonical_record":{"source":{"id":"1802.09932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T12:56:07Z","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"title_canon_sha256":"97a84c9e6e80cb7c9a1f880b2a6b00b5056280bf1156a20aaa827c9e32d14313","abstract_canon_sha256":"42928ccdd9a328107d4de68915663a60ff6fea30e05f44ee08c988d7955c1279"},"schema_version":"1.0"},"canonical_sha256":"8a22046ccff5683b7f716ed9e05d190d412dfb263044912e72218e2bda91bda1","source":{"kind":"arxiv","id":"1802.09932","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09932","created_at":"2026-05-18T00:02:01Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09932v2","created_at":"2026-05-18T00:02:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09932","created_at":"2026-05-18T00:02:01Z"},{"alias_kind":"pith_short_12","alias_value":"RIRAI3GP6VUD","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RIRAI3GP6VUDW73R","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RIRAI3GP","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RIRAI3GP6VUDW73RN3M6AXIZBV","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T12:56:07Z","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"title_canon_sha256":"97a84c9e6e80cb7c9a1f880b2a6b00b5056280bf1156a20aaa827c9e32d14313","abstract_canon_sha256":"42928ccdd9a328107d4de68915663a60ff6fea30e05f44ee08c988d7955c1279"},"schema_version":"1.0"},"canonical_sha256":"8a22046ccff5683b7f716ed9e05d190d412dfb263044912e72218e2bda91bda1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:01.544816Z","signature_b64":"XLIWrQ0C61wwJXfMNhukP98g1lmwD6DG4yzBmxviIMMzbHGgQ48y3dQN920wUCHi8QSc/LY0mZw5zvRjFnGbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a22046ccff5683b7f716ed9e05d190d412dfb263044912e72218e2bda91bda1","last_reissued_at":"2026-05-18T00:02:01.544208Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:01.544208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09932","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9lrqPQ48CchogwzS/ZAHyVtDL/P0OgVTbEkxm/DFARDAWGeddv+dCa/Gvj0JcJjMq790cBsMO7EXRrZXdwmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T18:47:59.998096Z"},"content_sha256":"f309672fa79d0833db376e19ab519a70cecf27ba406025ff540039e4720f38ed","schema_version":"1.0","event_id":"sha256:f309672fa79d0833db376e19ab519a70cecf27ba406025ff540039e4720f38ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RIRAI3GP6VUDW73RN3M6AXIZBV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Fanhua Shang, Hongying Liu, Ivor W. Tsang, James Cheng, Kaiwen Zhou, Licheng Jiao, Lijun Zhang","submitted_at":"2018-02-26T12:56:07Z","abstract_excerpt":"In this paper, we propose a simple variant of the original SVRG, called variance reduced stochastic gradient descent (VR-SGD). Unlike the choices of snapshot and starting points in SVRG and its proximal variant, Prox-SVRG, the two vectors of VR-SGD are set to the average and last iterate of the previous epoch, respectively. The settings allow us to use much larger learning rates, and also make our convergence analysis more challenging. We also design two different update rules for smooth and non-smooth objective functions, respectively, which means that VR-SGD can tackle non-smooth and/or non-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09932","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BTvXemp6NHyakfY9RMwvFNNk/NjeGs2stAK6h/yIop0XZs6psACfJlQP1MXBNbZVHPHG1bJ5s1vKXgIpKMPJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T18:47:59.998837Z"},"content_sha256":"65ca13c033526b489089091f86a52f246c5429c67b0a7fcdb8bcfa3b1503aac5","schema_version":"1.0","event_id":"sha256:65ca13c033526b489089091f86a52f246c5429c67b0a7fcdb8bcfa3b1503aac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RIRAI3GP6VUDW73RN3M6AXIZBV/bundle.json","state_url":"https://pith.science/pith/RIRAI3GP6VUDW73RN3M6AXIZBV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RIRAI3GP6VUDW73RN3M6AXIZBV/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":"2026-05-18T18:47:59Z","links":{"resolver":"https://pith.science/pith/RIRAI3GP6VUDW73RN3M6AXIZBV","bundle":"https://pith.science/pith/RIRAI3GP6VUDW73RN3M6AXIZBV/bundle.json","state":"https://pith.science/pith/RIRAI3GP6VUDW73RN3M6AXIZBV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RIRAI3GP6VUDW73RN3M6AXIZBV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RIRAI3GP6VUDW73RN3M6AXIZBV","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":"42928ccdd9a328107d4de68915663a60ff6fea30e05f44ee08c988d7955c1279","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T12:56:07Z","title_canon_sha256":"97a84c9e6e80cb7c9a1f880b2a6b00b5056280bf1156a20aaa827c9e32d14313"},"schema_version":"1.0","source":{"id":"1802.09932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09932","created_at":"2026-05-18T00:02:01Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09932v2","created_at":"2026-05-18T00:02:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09932","created_at":"2026-05-18T00:02:01Z"},{"alias_kind":"pith_short_12","alias_value":"RIRAI3GP6VUD","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RIRAI3GP6VUDW73R","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RIRAI3GP","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:65ca13c033526b489089091f86a52f246c5429c67b0a7fcdb8bcfa3b1503aac5","target":"graph","created_at":"2026-05-18T00:02:01Z","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 SVRG, called variance reduced stochastic gradient descent (VR-SGD). Unlike the choices of snapshot and starting points in SVRG and its proximal variant, Prox-SVRG, the two vectors of VR-SGD are set to the average and last iterate of the previous epoch, respectively. The settings allow us to use much larger learning rates, and also make our convergence analysis more challenging. We also design two different update rules for smooth and non-smooth objective functions, respectively, which means that VR-SGD can tackle non-smooth and/or non-","authors_text":"Dacheng Tao, Fanhua Shang, Hongying Liu, Ivor W. Tsang, James Cheng, Kaiwen Zhou, Licheng Jiao, Lijun Zhang","cross_cats":["cs.CV","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T12:56:07Z","title":"VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09932","kind":"arxiv","version":2},"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:f309672fa79d0833db376e19ab519a70cecf27ba406025ff540039e4720f38ed","target":"record","created_at":"2026-05-18T00:02:01Z","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":"42928ccdd9a328107d4de68915663a60ff6fea30e05f44ee08c988d7955c1279","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T12:56:07Z","title_canon_sha256":"97a84c9e6e80cb7c9a1f880b2a6b00b5056280bf1156a20aaa827c9e32d14313"},"schema_version":"1.0","source":{"id":"1802.09932","kind":"arxiv","version":2}},"canonical_sha256":"8a22046ccff5683b7f716ed9e05d190d412dfb263044912e72218e2bda91bda1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a22046ccff5683b7f716ed9e05d190d412dfb263044912e72218e2bda91bda1","first_computed_at":"2026-05-18T00:02:01.544208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:01.544208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XLIWrQ0C61wwJXfMNhukP98g1lmwD6DG4yzBmxviIMMzbHGgQ48y3dQN920wUCHi8QSc/LY0mZw5zvRjFnGbBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:01.544816Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f309672fa79d0833db376e19ab519a70cecf27ba406025ff540039e4720f38ed","sha256:65ca13c033526b489089091f86a52f246c5429c67b0a7fcdb8bcfa3b1503aac5"],"state_sha256":"46a26a17f24bcac9040b1d0022a02f8f26f9a5ca1811bd48349622eb9187f345"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AH/OpaX3mUovWTHDCrbmyOmCtUdmmBzK/FjT/rmjDpkaMb3P6DvREBRqEGlI63rPM0wJJ+KeoAvwc53QkBSJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T18:48:00.000939Z","bundle_sha256":"39e112b268b169fafab63691f315cb7f9970420a94a788ac7f9fa38cd2979f5b"}}