{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BEZOKLCNE5APAPMOTNK43LUM5N","short_pith_number":"pith:BEZOKLCN","canonical_record":{"source":{"id":"1610.00970","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T13:08:42Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"de6016a46174b655708558cddd0c2db875861b8e741a2b9b8d0dd2c2e7360a2b","abstract_canon_sha256":"8dc1ca94ef4537a5f717ba675ef94f4ecd6ee8b703ba5bd6dfc0859b70b41561"},"schema_version":"1.0"},"canonical_sha256":"0932e52c4d2740f03d8e9b55cdae8ceb660b8bf5141728ff28f6c4cf4aa8d55d","source":{"kind":"arxiv","id":"1610.00970","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00970","created_at":"2026-05-18T00:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00970v6","created_at":"2026-05-18T00:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00970","created_at":"2026-05-18T00:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"BEZOKLCNE5AP","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BEZOKLCNE5APAPMO","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BEZOKLCN","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BEZOKLCNE5APAPMOTNK43LUM5N","target":"record","payload":{"canonical_record":{"source":{"id":"1610.00970","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T13:08:42Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"de6016a46174b655708558cddd0c2db875861b8e741a2b9b8d0dd2c2e7360a2b","abstract_canon_sha256":"8dc1ca94ef4537a5f717ba675ef94f4ecd6ee8b703ba5bd6dfc0859b70b41561"},"schema_version":"1.0"},"canonical_sha256":"0932e52c4d2740f03d8e9b55cdae8ceb660b8bf5141728ff28f6c4cf4aa8d55d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:32.874062Z","signature_b64":"b77grDW1x5YRl43nVLWetLOVHzXHfyGTWDfDdIiEF9WwUCp78mEiSS/3QGwcobcywtBIZ4f130h/laVuvRMHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0932e52c4d2740f03d8e9b55cdae8ceb660b8bf5141728ff28f6c4cf4aa8d55d","last_reissued_at":"2026-05-18T00:30:32.873364Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:32.873364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.00970","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fH9Ko3GPMK67mm76xe3Bqd2H2Ooxl5bv64zbkryAOcudUZwStcsnVnj+G5XPDfFTe64C0YXayyUDHZksdOMtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:02:59.044120Z"},"content_sha256":"b70f9cff45e4f8c924aa5d48758d90686d974a08cd8dcc619afcd606e51ef9b6","schema_version":"1.0","event_id":"sha256:b70f9cff45e4f8c924aa5d48758d90686d974a08cd8dcc619afcd606e51ef9b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BEZOKLCNE5APAPMOTNK43LUM5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Alberto Bietti, Julien Mairal","submitted_at":"2016-10-04T13:08:42Z","abstract_excerpt":"Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for example by data augmentation. In such cases, the objective is no longer a finite sum, and the main candidate for optimization is the stochastic gradient descent method (SGD). In this paper, we introduce a variance reduction approach for these settings when the objective is composite and strongly convex. The convergence rate outperforms SGD with a typically much"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00970","kind":"arxiv","version":6},"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":"2026-05-18T00:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DpJlaKTgjbZSlT2Ub9m4JU64irTHNXw2/4/uqy4xi96nk9cHWO/q5QokEfUaFN4AxYypwSUXCxE4FH16dGSVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:02:59.044488Z"},"content_sha256":"c9e862835ff060543b8f61e79e545a136715d59af6f39b1edf7a477e5904374f","schema_version":"1.0","event_id":"sha256:c9e862835ff060543b8f61e79e545a136715d59af6f39b1edf7a477e5904374f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BEZOKLCNE5APAPMOTNK43LUM5N/bundle.json","state_url":"https://pith.science/pith/BEZOKLCNE5APAPMOTNK43LUM5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BEZOKLCNE5APAPMOTNK43LUM5N/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":"2026-06-02T05:02:59Z","links":{"resolver":"https://pith.science/pith/BEZOKLCNE5APAPMOTNK43LUM5N","bundle":"https://pith.science/pith/BEZOKLCNE5APAPMOTNK43LUM5N/bundle.json","state":"https://pith.science/pith/BEZOKLCNE5APAPMOTNK43LUM5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BEZOKLCNE5APAPMOTNK43LUM5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BEZOKLCNE5APAPMOTNK43LUM5N","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":"8dc1ca94ef4537a5f717ba675ef94f4ecd6ee8b703ba5bd6dfc0859b70b41561","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T13:08:42Z","title_canon_sha256":"de6016a46174b655708558cddd0c2db875861b8e741a2b9b8d0dd2c2e7360a2b"},"schema_version":"1.0","source":{"id":"1610.00970","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00970","created_at":"2026-05-18T00:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00970v6","created_at":"2026-05-18T00:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00970","created_at":"2026-05-18T00:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"BEZOKLCNE5AP","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BEZOKLCNE5APAPMO","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BEZOKLCN","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:c9e862835ff060543b8f61e79e545a136715d59af6f39b1edf7a477e5904374f","target":"graph","created_at":"2026-05-18T00:30:32Z","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":"Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for example by data augmentation. In such cases, the objective is no longer a finite sum, and the main candidate for optimization is the stochastic gradient descent method (SGD). In this paper, we introduce a variance reduction approach for these settings when the objective is composite and strongly convex. The convergence rate outperforms SGD with a typically much","authors_text":"Alberto Bietti, Julien Mairal","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T13:08:42Z","title":"Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00970","kind":"arxiv","version":6},"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:b70f9cff45e4f8c924aa5d48758d90686d974a08cd8dcc619afcd606e51ef9b6","target":"record","created_at":"2026-05-18T00:30:32Z","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":"8dc1ca94ef4537a5f717ba675ef94f4ecd6ee8b703ba5bd6dfc0859b70b41561","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-10-04T13:08:42Z","title_canon_sha256":"de6016a46174b655708558cddd0c2db875861b8e741a2b9b8d0dd2c2e7360a2b"},"schema_version":"1.0","source":{"id":"1610.00970","kind":"arxiv","version":6}},"canonical_sha256":"0932e52c4d2740f03d8e9b55cdae8ceb660b8bf5141728ff28f6c4cf4aa8d55d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0932e52c4d2740f03d8e9b55cdae8ceb660b8bf5141728ff28f6c4cf4aa8d55d","first_computed_at":"2026-05-18T00:30:32.873364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:32.873364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b77grDW1x5YRl43nVLWetLOVHzXHfyGTWDfDdIiEF9WwUCp78mEiSS/3QGwcobcywtBIZ4f130h/laVuvRMHAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:32.874062Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.00970","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b70f9cff45e4f8c924aa5d48758d90686d974a08cd8dcc619afcd606e51ef9b6","sha256:c9e862835ff060543b8f61e79e545a136715d59af6f39b1edf7a477e5904374f"],"state_sha256":"8a8b2d6d4312c400ce9e1193b92e6bd8e20e0bc75c263e15cb52d5fa3aaf09c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dqzoQuTW4eEBoWC6TepK4thoH2PREczIa+i4Wv/co2hLqXKiG6MA/YVG+Y4E5/4vcgcFQvyRd7lsXh71RrADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:02:59.046552Z","bundle_sha256":"d15f2504b5719ca12a386abdab84ffb8af4d575c4cc97db339010943300c2847"}}