{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YAN6L6S7J3G34GIZMSPFRQRUOJ","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":"ddfa2f07869533a90656aa8656a525815fb85f38cb6680a4d50d4b80d5102533","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T17:56:28Z","title_canon_sha256":"880db42f3546367acb3553da6df67b662300ebe91d8e250f41524d4053c95ddf"},"schema_version":"1.0","source":{"id":"1909.12292","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.12292","created_at":"2026-07-05T00:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"1909.12292v4","created_at":"2026-07-05T00:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12292","created_at":"2026-07-05T00:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"YAN6L6S7J3G3","created_at":"2026-07-05T00:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"YAN6L6S7J3G34GIZ","created_at":"2026-07-05T00:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"YAN6L6S7","created_at":"2026-07-05T00:40:58Z"}],"graph_snapshots":[{"event_id":"sha256:08b605d0d65c646e09b27a3f9f9fdf9f8bfa8f54d2a49f2a290125f5d20f79f5","target":"graph","created_at":"2026-07-05T00:40:58Z","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/1909.12292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent theoretical work has guaranteed that overparameterized networks trained by gradient descent achieve arbitrarily low training error, and sometimes even low test error. The required width, however, is always polynomial in at least one of the sample size $n$, the (inverse) target error $1/\\epsilon$, and the (inverse) failure probability $1/\\delta$. This work shows that $\\widetilde{\\Theta}(1/\\epsilon)$ iterations of gradient descent with $\\widetilde{\\Omega}(1/\\epsilon^2)$ training examples on two-layer ReLU networks of any width exceeding $\\mathrm{polylog}(n,1/\\epsilon,1/\\delta)$ suffice to","authors_text":"Matus Telgarsky, Ziwei Ji","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T17:56:28Z","title":"Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12292","kind":"arxiv","version":4},"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":"sha256:3bf4b543da0f97f1ca0a2878eaf84bf41176fce1dae4988e7606a3a71f223da6","target":"record","created_at":"2026-07-05T00:40:58Z","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":"ddfa2f07869533a90656aa8656a525815fb85f38cb6680a4d50d4b80d5102533","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T17:56:28Z","title_canon_sha256":"880db42f3546367acb3553da6df67b662300ebe91d8e250f41524d4053c95ddf"},"schema_version":"1.0","source":{"id":"1909.12292","kind":"arxiv","version":4}},"canonical_sha256":"c01be5fa5f4ecdbe1919649e58c234727193538bea383f1326e1841db0be7795","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c01be5fa5f4ecdbe1919649e58c234727193538bea383f1326e1841db0be7795","first_computed_at":"2026-07-05T00:40:58.659971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:40:58.659971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MXZHiYwNVDj+BLDhso+I5QIv/p+0bXvu5fyxcl6MFnBzHw4pY6MJBSRZqggb0ZaiftFa+33hXwdhW791xSiPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:40:58.660405Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.12292","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bf4b543da0f97f1ca0a2878eaf84bf41176fce1dae4988e7606a3a71f223da6","sha256:08b605d0d65c646e09b27a3f9f9fdf9f8bfa8f54d2a49f2a290125f5d20f79f5"],"state_sha256":"a62a2f1bf6c4320a73007261023f58e018bd1a48fb1aa1cd1d0ec33132eb4f4f"}