{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:A5WVWIDYRTQDKKOVK7WBSUY4RP","short_pith_number":"pith:A5WVWIDY","canonical_record":{"source":{"id":"1806.02927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-08T00:06:41Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2bb5369e49facd1719db8da83610f8094c960cbe7b05b1712a23bf7cb0b94f46","abstract_canon_sha256":"ffe4d6cb1e217c9dbfe323226f587137344d0cd67dc4965f60c1fb31dd07caf4"},"schema_version":"1.0"},"canonical_sha256":"076d5b20788ce03529d557ec19531c8bcd68c1710e63a92f6921c8325b0c42e4","source":{"kind":"arxiv","id":"1806.02927","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02927","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02927v1","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02927","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"A5WVWIDYRTQD","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A5WVWIDYRTQDKKOV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A5WVWIDY","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:A5WVWIDYRTQDKKOVK7WBSUY4RP","target":"record","payload":{"canonical_record":{"source":{"id":"1806.02927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-08T00:06:41Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2bb5369e49facd1719db8da83610f8094c960cbe7b05b1712a23bf7cb0b94f46","abstract_canon_sha256":"ffe4d6cb1e217c9dbfe323226f587137344d0cd67dc4965f60c1fb31dd07caf4"},"schema_version":"1.0"},"canonical_sha256":"076d5b20788ce03529d557ec19531c8bcd68c1710e63a92f6921c8325b0c42e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:54.286735Z","signature_b64":"k/JN63kigwVu7w/mY2I73KMgYiUfbpn7RV+LtM/mX4CMTIL8+g5yZKA0G3+mV6ze6khwPh4eaVwk7JFRuf6RAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076d5b20788ce03529d557ec19531c8bcd68c1710e63a92f6921c8325b0c42e4","last_reissued_at":"2026-05-18T00:13:54.286019Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:54.286019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.02927","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":"2026-05-18T00:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAXpH8UEY8doW/e2YEL9KQTi5TiXf7BzfycGUmTboxIELo/llDI1ceGzBI0okyP4JOMmDd3mqo+IXCmXDS7qAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:31:37.479913Z"},"content_sha256":"ecdf8d9617c1a4447bf4f061efbdd8dfb25273fafd758f2ee4b4b891a0c1efd5","schema_version":"1.0","event_id":"sha256:ecdf8d9617c1a4447bf4f061efbdd8dfb25273fafd758f2ee4b4b891a0c1efd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:A5WVWIDYRTQDKKOVK7WBSUY4RP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"James T. Kwok, Shuai Zheng","submitted_at":"2018-06-08T00:06:41Z","abstract_excerpt":"Variance reduction has been commonly used in stochastic optimization. It relies crucially on the assumption that the data set is finite. However, when the data are imputed with random noise as in data augmentation, the perturbed data set be- comes essentially infinite. Recently, the stochastic MISO (S-MISO) algorithm is introduced to address this expected risk minimization problem. Though it converges faster than SGD, a significant amount of memory is required. In this pa- per, we propose two SGD-like algorithms for expected risk minimization with random perturbation, namely, stochastic sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02927","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":"2026-05-18T00:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWxXirg81cZD8/KG4ytD/JhOI6OA3WUJ8EWfWyQqP5Sv1712ZXIRwb4pJKTGDrvwrluwacxq+AGkfdZbpGHaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:31:37.480304Z"},"content_sha256":"285dcc59990bbf89972f2179d39166f199dd55af28f1cd6db350fc33b19ce15f","schema_version":"1.0","event_id":"sha256:285dcc59990bbf89972f2179d39166f199dd55af28f1cd6db350fc33b19ce15f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP/bundle.json","state_url":"https://pith.science/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP/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":"2026-05-30T00:31:37Z","links":{"resolver":"https://pith.science/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP","bundle":"https://pith.science/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP/bundle.json","state":"https://pith.science/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5WVWIDYRTQDKKOVK7WBSUY4RP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A5WVWIDYRTQDKKOVK7WBSUY4RP","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":"ffe4d6cb1e217c9dbfe323226f587137344d0cd67dc4965f60c1fb31dd07caf4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-08T00:06:41Z","title_canon_sha256":"2bb5369e49facd1719db8da83610f8094c960cbe7b05b1712a23bf7cb0b94f46"},"schema_version":"1.0","source":{"id":"1806.02927","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02927","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02927v1","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02927","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"A5WVWIDYRTQD","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A5WVWIDYRTQDKKOV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A5WVWIDY","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:285dcc59990bbf89972f2179d39166f199dd55af28f1cd6db350fc33b19ce15f","target":"graph","created_at":"2026-05-18T00:13:54Z","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":"Variance reduction has been commonly used in stochastic optimization. It relies crucially on the assumption that the data set is finite. However, when the data are imputed with random noise as in data augmentation, the perturbed data set be- comes essentially infinite. Recently, the stochastic MISO (S-MISO) algorithm is introduced to address this expected risk minimization problem. Though it converges faster than SGD, a significant amount of memory is required. In this pa- per, we propose two SGD-like algorithms for expected risk minimization with random perturbation, namely, stochastic sample","authors_text":"James T. Kwok, Shuai Zheng","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-08T00:06:41Z","title":"Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02927","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:ecdf8d9617c1a4447bf4f061efbdd8dfb25273fafd758f2ee4b4b891a0c1efd5","target":"record","created_at":"2026-05-18T00:13:54Z","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":"ffe4d6cb1e217c9dbfe323226f587137344d0cd67dc4965f60c1fb31dd07caf4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-08T00:06:41Z","title_canon_sha256":"2bb5369e49facd1719db8da83610f8094c960cbe7b05b1712a23bf7cb0b94f46"},"schema_version":"1.0","source":{"id":"1806.02927","kind":"arxiv","version":1}},"canonical_sha256":"076d5b20788ce03529d557ec19531c8bcd68c1710e63a92f6921c8325b0c42e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"076d5b20788ce03529d557ec19531c8bcd68c1710e63a92f6921c8325b0c42e4","first_computed_at":"2026-05-18T00:13:54.286019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:54.286019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k/JN63kigwVu7w/mY2I73KMgYiUfbpn7RV+LtM/mX4CMTIL8+g5yZKA0G3+mV6ze6khwPh4eaVwk7JFRuf6RAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:54.286735Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02927","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecdf8d9617c1a4447bf4f061efbdd8dfb25273fafd758f2ee4b4b891a0c1efd5","sha256:285dcc59990bbf89972f2179d39166f199dd55af28f1cd6db350fc33b19ce15f"],"state_sha256":"c2ac35f2d120bec8fd117a2f72e58e7f0dbb14e502cc734b2fdb68bd41a9169c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSfZ1nJJ/CiIGyfc47++ehvrxxYitPg3SS4yAoHrazQVKLtRkp2AYvTxa/sH1Bl4SONzfH9HwCZCLMf8bNVaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T00:31:37.484563Z","bundle_sha256":"d6f4c420ea81b722f025fe2e50a70f5da46b0ecc122dce6af90a03e6859b411c"}}