{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FTKGCEUK3WPR5L3PIRHMLE2EKY","short_pith_number":"pith:FTKGCEUK","schema_version":"1.0","canonical_sha256":"2cd461128add9f1eaf6f444ec59344560d3a341aee5c0f9c711110398bd97a9c","source":{"kind":"arxiv","id":"2412.17518","version":1},"attestation_state":"computed","paper":{"title":"Optimal Convergence Rates for Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mike Nguyen, Nicole M\\\"ucke","submitted_at":"2024-12-23T12:31:38Z","abstract_excerpt":"We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to be minimax optimal within the framework of non-parametric regression in reproducing kernel Hilbert spaces (RKHS). We provide bounds on the number of hidden neurons and the number of second-stage samples necessary for generalization. To justify our NTK regime, we additionally show that any operator approximable by a neural operator can also be approximated by an operator from th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.17518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-23T12:31:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff6736b9c56a7d955fa882b33c2ef383ddabe520c97e46128aeec91bded59ef9","abstract_canon_sha256":"d97358026a249b4b1b886fd690d9cf7bf4f4359281fcf0c7e9977d9c0df07334"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:23.576391Z","signature_b64":"XYr0w9iecZJKOEdINP7hnrq3Sr5332mmjKoQ0cKywyHUAXHZtvKycPK0FI6mtBHz44z1Y2vjO2bqsE+kmtqZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd461128add9f1eaf6f444ec59344560d3a341aee5c0f9c711110398bd97a9c","last_reissued_at":"2026-07-05T09:53:23.575902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:23.575902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Convergence Rates for Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mike Nguyen, Nicole M\\\"ucke","submitted_at":"2024-12-23T12:31:38Z","abstract_excerpt":"We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to be minimax optimal within the framework of non-parametric regression in reproducing kernel Hilbert spaces (RKHS). We provide bounds on the number of hidden neurons and the number of second-stage samples necessary for generalization. To justify our NTK regime, we additionally show that any operator approximable by a neural operator can also be approximated by an operator from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17518","kind":"arxiv","version":1},"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/2412.17518/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.17518","created_at":"2026-07-05T09:53:23.575962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17518v1","created_at":"2026-07-05T09:53:23.575962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17518","created_at":"2026-07-05T09:53:23.575962+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTKGCEUK3WPR","created_at":"2026-07-05T09:53:23.575962+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTKGCEUK3WPR5L3P","created_at":"2026-07-05T09:53:23.575962+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTKGCEUK","created_at":"2026-07-05T09:53:23.575962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00479","citing_title":"Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14370","citing_title":"Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY","json":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY.json","graph_json":"https://pith.science/api/pith-number/FTKGCEUK3WPR5L3PIRHMLE2EKY/graph.json","events_json":"https://pith.science/api/pith-number/FTKGCEUK3WPR5L3PIRHMLE2EKY/events.json","paper":"https://pith.science/paper/FTKGCEUK"},"agent_actions":{"view_html":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY","download_json":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY.json","view_paper":"https://pith.science/paper/FTKGCEUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17518&json=true","fetch_graph":"https://pith.science/api/pith-number/FTKGCEUK3WPR5L3PIRHMLE2EKY/graph.json","fetch_events":"https://pith.science/api/pith-number/FTKGCEUK3WPR5L3PIRHMLE2EKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY/action/storage_attestation","attest_author":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY/action/author_attestation","sign_citation":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY/action/citation_signature","submit_replication":"https://pith.science/pith/FTKGCEUK3WPR5L3PIRHMLE2EKY/action/replication_record"}},"created_at":"2026-07-05T09:53:23.575962+00:00","updated_at":"2026-07-05T09:53:23.575962+00:00"}