{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:JVB6JDCSX3IFDZJCIZOAGA7M57","short_pith_number":"pith:JVB6JDCS","canonical_record":{"source":{"id":"1604.03257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-04-12T06:24:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbe9efd19906746370aa65eaec99e968fa5e823559eb2610ae30921668ac8ea2","abstract_canon_sha256":"2b0b37bb0cd489bc71566624c1f17ed7f846717779655baa2961e9754c165ee7"},"schema_version":"1.0"},"canonical_sha256":"4d43e48c52bed051e522465c0303ecefcda2b7d3638b9f78488101dedd94be52","source":{"kind":"arxiv","id":"1604.03257","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03257","created_at":"2026-05-18T01:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03257v2","created_at":"2026-05-18T01:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03257","created_at":"2026-05-18T01:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"JVB6JDCSX3IF","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JVB6JDCSX3IFDZJC","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JVB6JDCS","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:JVB6JDCSX3IFDZJCIZOAGA7M57","target":"record","payload":{"canonical_record":{"source":{"id":"1604.03257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-04-12T06:24:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbe9efd19906746370aa65eaec99e968fa5e823559eb2610ae30921668ac8ea2","abstract_canon_sha256":"2b0b37bb0cd489bc71566624c1f17ed7f846717779655baa2961e9754c165ee7"},"schema_version":"1.0"},"canonical_sha256":"4d43e48c52bed051e522465c0303ecefcda2b7d3638b9f78488101dedd94be52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:33.933046Z","signature_b64":"IE5zpad/gwT3LiebuXtM2S6iiK8Mp0OLsswg0LB3plt2B52aSVx0ON2lETWlsZtZUugcXViBQsiz3ZCv2E36DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d43e48c52bed051e522465c0303ecefcda2b7d3638b9f78488101dedd94be52","last_reissued_at":"2026-05-18T01:15:33.932413Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:33.932413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.03257","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":"2026-05-18T01:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GqJuborRhu1hx5/kg6rdzhG3s/ustRQr7geHL/LF9vU/x5iiwkukyMpI/1kW04icDD71YLPXR6Ij2T70dBzhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:33:40.298677Z"},"content_sha256":"e0d084882c42bccb9712963082f4f893e59faf9d1037c2b2fa8642d853d2ac43","schema_version":"1.0","event_id":"sha256:e0d084882c42bccb9712963082f4f893e59faf9d1037c2b2fa8642d853d2ac43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:JVB6JDCSX3IFDZJCIZOAGA7M57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Qihang Lin, Tianbao Yang, Zhe Li","submitted_at":"2016-04-12T06:24:19Z","abstract_excerpt":"Recently, {\\it stochastic momentum} methods have been widely adopted in training deep neural networks. However, their convergence analysis is still underexplored at the moment, in particular for non-convex optimization. This paper fills the gap between practice and theory by developing a basic convergence analysis of two stochastic momentum methods, namely stochastic heavy-ball method and the stochastic variant of Nesterov's accelerated gradient method. We hope that the basic convergence results developed in this paper can serve the reference to the convergence of stochastic momentum methods a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03257","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":"2026-05-18T01:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tdHASwljZIrHG5t4nfJSm5locPwIO5ziMfs78vmffbECiWmxZa2UrMUw6nrW1MKQ92HoI+Jg2VqkUAj7aHCtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:33:40.299346Z"},"content_sha256":"23402c00ce840d22f7582231ddef5d76a41b8ccafe105b058fa0c3e570bf4456","schema_version":"1.0","event_id":"sha256:23402c00ce840d22f7582231ddef5d76a41b8ccafe105b058fa0c3e570bf4456"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVB6JDCSX3IFDZJCIZOAGA7M57/bundle.json","state_url":"https://pith.science/pith/JVB6JDCSX3IFDZJCIZOAGA7M57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVB6JDCSX3IFDZJCIZOAGA7M57/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":"2026-06-06T18:33:40Z","links":{"resolver":"https://pith.science/pith/JVB6JDCSX3IFDZJCIZOAGA7M57","bundle":"https://pith.science/pith/JVB6JDCSX3IFDZJCIZOAGA7M57/bundle.json","state":"https://pith.science/pith/JVB6JDCSX3IFDZJCIZOAGA7M57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVB6JDCSX3IFDZJCIZOAGA7M57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:JVB6JDCSX3IFDZJCIZOAGA7M57","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":"2b0b37bb0cd489bc71566624c1f17ed7f846717779655baa2961e9754c165ee7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-04-12T06:24:19Z","title_canon_sha256":"bbe9efd19906746370aa65eaec99e968fa5e823559eb2610ae30921668ac8ea2"},"schema_version":"1.0","source":{"id":"1604.03257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03257","created_at":"2026-05-18T01:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03257v2","created_at":"2026-05-18T01:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03257","created_at":"2026-05-18T01:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"JVB6JDCSX3IF","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JVB6JDCSX3IFDZJC","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JVB6JDCS","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:23402c00ce840d22f7582231ddef5d76a41b8ccafe105b058fa0c3e570bf4456","target":"graph","created_at":"2026-05-18T01:15:33Z","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":"Recently, {\\it stochastic momentum} methods have been widely adopted in training deep neural networks. However, their convergence analysis is still underexplored at the moment, in particular for non-convex optimization. This paper fills the gap between practice and theory by developing a basic convergence analysis of two stochastic momentum methods, namely stochastic heavy-ball method and the stochastic variant of Nesterov's accelerated gradient method. We hope that the basic convergence results developed in this paper can serve the reference to the convergence of stochastic momentum methods a","authors_text":"Qihang Lin, Tianbao Yang, Zhe Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-04-12T06:24:19Z","title":"Unified Convergence Analysis of Stochastic Momentum Methods for Convex and Non-convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03257","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:e0d084882c42bccb9712963082f4f893e59faf9d1037c2b2fa8642d853d2ac43","target":"record","created_at":"2026-05-18T01:15:33Z","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":"2b0b37bb0cd489bc71566624c1f17ed7f846717779655baa2961e9754c165ee7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-04-12T06:24:19Z","title_canon_sha256":"bbe9efd19906746370aa65eaec99e968fa5e823559eb2610ae30921668ac8ea2"},"schema_version":"1.0","source":{"id":"1604.03257","kind":"arxiv","version":2}},"canonical_sha256":"4d43e48c52bed051e522465c0303ecefcda2b7d3638b9f78488101dedd94be52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d43e48c52bed051e522465c0303ecefcda2b7d3638b9f78488101dedd94be52","first_computed_at":"2026-05-18T01:15:33.932413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:33.932413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IE5zpad/gwT3LiebuXtM2S6iiK8Mp0OLsswg0LB3plt2B52aSVx0ON2lETWlsZtZUugcXViBQsiz3ZCv2E36DA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:33.933046Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.03257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0d084882c42bccb9712963082f4f893e59faf9d1037c2b2fa8642d853d2ac43","sha256:23402c00ce840d22f7582231ddef5d76a41b8ccafe105b058fa0c3e570bf4456"],"state_sha256":"7ca9c61a0bcc4cc29cd5beedb0e511e5144aa06ceb103875ca027ba77f0e85c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JdjItMXCnx3oxWipQ7fgTdYUCwsOUnKbBVGXPDDA1GjSLvIyqcrUioRadxPgRWPTn0/sdSCJKfQmBJE/KnD6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:33:40.302740Z","bundle_sha256":"b4b337d73b8d8d780e9cf77e9df8dea480c52dccd66cc4ac06858945578283d8"}}