{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PMQNFFQI27XDGPTZEZHGPXJMNR","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":"93b772f9f8e3c7d381ddfd025b3bedfd569dc52f9042c5c3f329c1ececf3d47c","cross_cats_sorted":["cond-mat.dis-nn","cs.NE","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T15:22:51Z","title_canon_sha256":"43de1bab1aabcb1a2406d4ce4d6ce3d4c85fca5c284e1ccb8778d54c766485b5"},"schema_version":"1.0","source":{"id":"2308.01814","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01814","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01814v2","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01814","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_12","alias_value":"PMQNFFQI27XD","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_16","alias_value":"PMQNFFQI27XDGPTZ","created_at":"2026-07-05T06:38:03Z"},{"alias_kind":"pith_short_8","alias_value":"PMQNFFQI","created_at":"2026-07-05T06:38:03Z"}],"graph_snapshots":[{"event_id":"sha256:318ac950a2b263de098ef4ad3328fd2f06fc1fe825ff99b68668bc13535eff93","target":"graph","created_at":"2026-07-05T06:38:03Z","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/2308.01814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Going beyond stochastic gradient descent (SGD), what new phenomena emerge in wide neural networks trained by adaptive optimizers like Adam? Here we show: The same dichotomy between feature learning and kernel behaviors (as in SGD) holds for general optimizers as well, including Adam -- albeit with a nonlinear notion of \"kernel.\" We derive the corresponding \"neural tangent\" and \"maximal update\" limits for any architecture. Two foundational advances underlie the above results: 1) A new Tensor Program language, NEXORT, that can express how adaptive optimizers process gradients into updates. 2) Th","authors_text":"Etai Littwin, Greg Yang","cross_cats":["cond-mat.dis-nn","cs.NE","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T15:22:51Z","title":"Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01814","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:fd37bfb5cb59fd3c4366c5c8a304c2f824b0af0658c522ab647350f62bbe1fe7","target":"record","created_at":"2026-07-05T06:38:03Z","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":"93b772f9f8e3c7d381ddfd025b3bedfd569dc52f9042c5c3f329c1ececf3d47c","cross_cats_sorted":["cond-mat.dis-nn","cs.NE","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T15:22:51Z","title_canon_sha256":"43de1bab1aabcb1a2406d4ce4d6ce3d4c85fca5c284e1ccb8778d54c766485b5"},"schema_version":"1.0","source":{"id":"2308.01814","kind":"arxiv","version":2}},"canonical_sha256":"7b20d29608d7ee333e79264e67dd2c6c72afc61e73da1c4ebd55afa7045e8352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b20d29608d7ee333e79264e67dd2c6c72afc61e73da1c4ebd55afa7045e8352","first_computed_at":"2026-07-05T06:38:03.310436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:38:03.310436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v+01YV4p3Wk2cNn3dmPkHHE2LensIZeAOha+O3rsgt77XbNwMCjMtbyASOStwng7Tg+aa5N7J7cls0OKVwrmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:38:03.310849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01814","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd37bfb5cb59fd3c4366c5c8a304c2f824b0af0658c522ab647350f62bbe1fe7","sha256:318ac950a2b263de098ef4ad3328fd2f06fc1fe825ff99b68668bc13535eff93"],"state_sha256":"9879e68834557b581db9492c7c2edf3a4d2f4c1d2185acd5a64bde5edc1dc356"}