{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BEFXZ2WZRGUEQWHH5DIULSFNAJ","short_pith_number":"pith:BEFXZ2WZ","canonical_record":{"source":{"id":"1902.07111","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T16:08:55Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"3e2f7b0c6c7b3b4afa7a88f2e009daf1a46aca2588d6560fa124f62abeba2b82","abstract_canon_sha256":"b3dc6363e3bd3a7eeaddc3c2a8b4f3de5d300f095e8482c587630d042c223b8b"},"schema_version":"1.0"},"canonical_sha256":"090b7cead989a84858e7e8d145c8ad025796660aacc2a926911e33e42924823c","source":{"kind":"arxiv","id":"1902.07111","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07111","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07111v2","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07111","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"BEFXZ2WZRGUE","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"BEFXZ2WZRGUEQWHH","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"BEFXZ2WZ","created_at":"2026-07-05T00:13:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BEFXZ2WZRGUEQWHH5DIULSFNAJ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07111","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T16:08:55Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"3e2f7b0c6c7b3b4afa7a88f2e009daf1a46aca2588d6560fa124f62abeba2b82","abstract_canon_sha256":"b3dc6363e3bd3a7eeaddc3c2a8b4f3de5d300f095e8482c587630d042c223b8b"},"schema_version":"1.0"},"canonical_sha256":"090b7cead989a84858e7e8d145c8ad025796660aacc2a926911e33e42924823c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:13.536538Z","signature_b64":"aXd4qnWipvA01KyL37PnOFRqe+Q3E31kmgIwU6IPTbhCe8zmTm8xlSwa9x+ebAKnaFLyVMHhCSOdJRvlj0P4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"090b7cead989a84858e7e8d145c8ad025796660aacc2a926911e33e42924823c","last_reissued_at":"2026-07-05T00:13:13.536007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:13.536007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07111","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":"2026-07-05T00:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ocOxGivYtVpNPzMoiOy7AWXSK0ieabziUCCDuYSy65/FJuZDAbOHBwozSanbhrb/GW3Wj1kCxBAvlHNin1ouBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:20:35.636579Z"},"content_sha256":"35f8344dc6cbfbb8983fd5e525b5a38ab49aba143789696b0d321aa229294d30","schema_version":"1.0","event_id":"sha256:35f8344dc6cbfbb8983fd5e525b5a38ab49aba143789696b0d321aa229294d30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BEFXZ2WZRGUEQWHH5DIULSFNAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rachel Ward, Simon S. Du, Xiaoxia Wu","submitted_at":"2019-02-19T16:08:55Z","abstract_excerpt":"Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee convergence to a stationary point. We propose an adaptive gradient method and show that for two-layer over-parameterized neural networks -- if the width is sufficiently large (polynomially) -- then the proposed method converges \\emph{to the global minimum} in polynomial time, and convergence is robust, \\emph{ without the need to fine-tune hyper-parameters such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07111","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1902.07111/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+tplGASt3t63y7PYu2NEZELjB0SzVOsfPAavxTpKDV3qM99P+jeBUa8mu1Vs6YopiiDu9txeJSvce5RZMHmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:20:35.637100Z"},"content_sha256":"b551a8949101f420b3a99e54dcfd3765ea27c3ae59cba9a84dadd2136296c4cb","schema_version":"1.0","event_id":"sha256:b551a8949101f420b3a99e54dcfd3765ea27c3ae59cba9a84dadd2136296c4cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ/bundle.json","state_url":"https://pith.science/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ/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":"2026-08-12T12:20:35Z","links":{"resolver":"https://pith.science/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ","bundle":"https://pith.science/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ/bundle.json","state":"https://pith.science/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BEFXZ2WZRGUEQWHH5DIULSFNAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BEFXZ2WZRGUEQWHH5DIULSFNAJ","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":"b3dc6363e3bd3a7eeaddc3c2a8b4f3de5d300f095e8482c587630d042c223b8b","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T16:08:55Z","title_canon_sha256":"3e2f7b0c6c7b3b4afa7a88f2e009daf1a46aca2588d6560fa124f62abeba2b82"},"schema_version":"1.0","source":{"id":"1902.07111","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07111","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07111v2","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07111","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"BEFXZ2WZRGUE","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"BEFXZ2WZRGUEQWHH","created_at":"2026-07-05T00:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"BEFXZ2WZ","created_at":"2026-07-05T00:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:b551a8949101f420b3a99e54dcfd3765ea27c3ae59cba9a84dadd2136296c4cb","target":"graph","created_at":"2026-07-05T00:13:13Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1902.07111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee convergence to a stationary point. We propose an adaptive gradient method and show that for two-layer over-parameterized neural networks -- if the width is sufficiently large (polynomially) -- then the proposed method converges \\emph{to the global minimum} in polynomial time, and convergence is robust, \\emph{ without the need to fine-tune hyper-parameters such a","authors_text":"Rachel Ward, Simon S. Du, Xiaoxia Wu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T16:08:55Z","title":"Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07111","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":"sha256:35f8344dc6cbfbb8983fd5e525b5a38ab49aba143789696b0d321aa229294d30","target":"record","created_at":"2026-07-05T00:13:13Z","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":"b3dc6363e3bd3a7eeaddc3c2a8b4f3de5d300f095e8482c587630d042c223b8b","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-19T16:08:55Z","title_canon_sha256":"3e2f7b0c6c7b3b4afa7a88f2e009daf1a46aca2588d6560fa124f62abeba2b82"},"schema_version":"1.0","source":{"id":"1902.07111","kind":"arxiv","version":2}},"canonical_sha256":"090b7cead989a84858e7e8d145c8ad025796660aacc2a926911e33e42924823c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"090b7cead989a84858e7e8d145c8ad025796660aacc2a926911e33e42924823c","first_computed_at":"2026-07-05T00:13:13.536007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:13.536007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aXd4qnWipvA01KyL37PnOFRqe+Q3E31kmgIwU6IPTbhCe8zmTm8xlSwa9x+ebAKnaFLyVMHhCSOdJRvlj0P4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:13.536538Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07111","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35f8344dc6cbfbb8983fd5e525b5a38ab49aba143789696b0d321aa229294d30","sha256:b551a8949101f420b3a99e54dcfd3765ea27c3ae59cba9a84dadd2136296c4cb"],"state_sha256":"f76b2a4c46cf8390937af3584cba21e5ffcfd8be617cc3e5b4a77c547819d721"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/20IbZ0k0uYxzuscTMl3MG8SrS9Z/MAXe3CKuJEiBCUIMO7wtDIUxtBIXGMdxqnQMQj1GgAv+xviuRRfV58Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:20:35.642156Z","bundle_sha256":"248201dbc34511c00abaf5acde722568678b7fe96ee24227a28d7533c7c9e72c"}}