{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:P2PLKRGRCJPTQPTMCJPYXBVPPV","short_pith_number":"pith:P2PLKRGR","canonical_record":{"source":{"id":"1801.06159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-18T18:23:02Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"e608b5c3c668296bc623adcca3bc7fe1f8d44513d4d2b49c2ad2e6188d391225","abstract_canon_sha256":"3456a775b5e27747646015f3079e3190f24ce2717e9f30d2786debcff59964ad"},"schema_version":"1.0"},"canonical_sha256":"7e9eb544d1125f383e6c125f8b86af7d721fe44a44488a3cae933a5bc02b041f","source":{"kind":"arxiv","id":"1801.06159","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.06159","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"1801.06159v2","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06159","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"P2PLKRGRCJPT","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P2PLKRGRCJPTQPTM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P2PLKRGR","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:P2PLKRGRCJPTQPTMCJPYXBVPPV","target":"record","payload":{"canonical_record":{"source":{"id":"1801.06159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-18T18:23:02Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"e608b5c3c668296bc623adcca3bc7fe1f8d44513d4d2b49c2ad2e6188d391225","abstract_canon_sha256":"3456a775b5e27747646015f3079e3190f24ce2717e9f30d2786debcff59964ad"},"schema_version":"1.0"},"canonical_sha256":"7e9eb544d1125f383e6c125f8b86af7d721fe44a44488a3cae933a5bc02b041f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:32.325603Z","signature_b64":"kDiHe6BgrHEgr32IBhL0/Cxajz2i+A4qfRinlG8sa1IXX6Rq/Sl6re9T62FXLGIwUGWDpJ1aifYNY+8RXcPTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9eb544d1125f383e6c125f8b86af7d721fe44a44488a3cae933a5bc02b041f","last_reissued_at":"2026-05-17T23:57:32.325025Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:32.325025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.06159","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":"2026-05-17T23:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qv/oIZ/xO4ykGzignlRfw+6KFxv6hbSrRgysa9/c/+A2Jh8VPhU3wNbfJ3nGwbqiGdx0DGm6wRib3vsacuuZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:02:00.672053Z"},"content_sha256":"2410302bd21ef2280d5f1fdc94c91b0e27fa6d13b5191495fc8291b323f02159","schema_version":"1.0","event_id":"sha256:2410302bd21ef2280d5f1fdc94c91b0e27fa6d13b5191495fc8291b323f02159"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:P2PLKRGRCJPTQPTMCJPYXBVPPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Does Stochastic Gradient Algorithm Work Well?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Dzung T. Phan, Jayant R. Kalagnanam, Katya Scheinberg, Lam M. Nguyen, Nam H. Nguyen","submitted_at":"2018-01-18T18:23:02Z","abstract_excerpt":"In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a fixed, large step size and propose a novel assumption on the objective function, under which this method has the improved convergence rates (to a neighborhood of the optimal solutions). We then empirically demonstrate that these assumptions hold for logistic regression and standard deep neural networks on classical data sets. Thus our analysis helps to expla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06159","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":"2026-05-17T23:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FsSHO/ugS7yY45rVrLmbvzfKFBMjAt9nKzq8aS+03Et+dJQl4vaWsWHL7qGw9RMO7+bUyGnaGWXKZ556XNUPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T22:02:00.672740Z"},"content_sha256":"8a3cc76a881c413d68d89ce14dca30f455f0503262317400ae5aeba9951e4c29","schema_version":"1.0","event_id":"sha256:8a3cc76a881c413d68d89ce14dca30f455f0503262317400ae5aeba9951e4c29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV/bundle.json","state_url":"https://pith.science/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV/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":"2026-05-26T22:02:00Z","links":{"resolver":"https://pith.science/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV","bundle":"https://pith.science/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV/bundle.json","state":"https://pith.science/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2PLKRGRCJPTQPTMCJPYXBVPPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:P2PLKRGRCJPTQPTMCJPYXBVPPV","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":"3456a775b5e27747646015f3079e3190f24ce2717e9f30d2786debcff59964ad","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-18T18:23:02Z","title_canon_sha256":"e608b5c3c668296bc623adcca3bc7fe1f8d44513d4d2b49c2ad2e6188d391225"},"schema_version":"1.0","source":{"id":"1801.06159","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.06159","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"1801.06159v2","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.06159","created_at":"2026-05-17T23:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"P2PLKRGRCJPT","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P2PLKRGRCJPTQPTM","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P2PLKRGR","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:8a3cc76a881c413d68d89ce14dca30f455f0503262317400ae5aeba9951e4c29","target":"graph","created_at":"2026-05-17T23:57:32Z","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":"In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a fixed, large step size and propose a novel assumption on the objective function, under which this method has the improved convergence rates (to a neighborhood of the optimal solutions). We then empirically demonstrate that these assumptions hold for logistic regression and standard deep neural networks on classical data sets. Thus our analysis helps to expla","authors_text":"Dzung T. Phan, Jayant R. Kalagnanam, Katya Scheinberg, Lam M. Nguyen, Nam H. Nguyen","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-18T18:23:02Z","title":"When Does Stochastic Gradient Algorithm Work Well?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.06159","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":"sha256:2410302bd21ef2280d5f1fdc94c91b0e27fa6d13b5191495fc8291b323f02159","target":"record","created_at":"2026-05-17T23:57:32Z","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":"3456a775b5e27747646015f3079e3190f24ce2717e9f30d2786debcff59964ad","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-18T18:23:02Z","title_canon_sha256":"e608b5c3c668296bc623adcca3bc7fe1f8d44513d4d2b49c2ad2e6188d391225"},"schema_version":"1.0","source":{"id":"1801.06159","kind":"arxiv","version":2}},"canonical_sha256":"7e9eb544d1125f383e6c125f8b86af7d721fe44a44488a3cae933a5bc02b041f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e9eb544d1125f383e6c125f8b86af7d721fe44a44488a3cae933a5bc02b041f","first_computed_at":"2026-05-17T23:57:32.325025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:32.325025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kDiHe6BgrHEgr32IBhL0/Cxajz2i+A4qfRinlG8sa1IXX6Rq/Sl6re9T62FXLGIwUGWDpJ1aifYNY+8RXcPTDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:32.325603Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.06159","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2410302bd21ef2280d5f1fdc94c91b0e27fa6d13b5191495fc8291b323f02159","sha256:8a3cc76a881c413d68d89ce14dca30f455f0503262317400ae5aeba9951e4c29"],"state_sha256":"a6b0b3c36e68f7b3e4e5c0275b414ac9feeb2db030f7391784241df528ab8305"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kw7ZwjQI4pyGSYqUwnKy5yiLuc3KSSARSp2ih7IXXCAUJ4B5poB4MCNZ5V1pNPDchi1iB3qInahH/qmM+qb0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T22:02:00.675890Z","bundle_sha256":"edcf4b6fb5e942d301c567e03ba4f964ae71fae9c0a43ab47619ee9133c5f9e7"}}