{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2B3TGSGJNK4NY6ECVGGAT6L5N6","short_pith_number":"pith:2B3TGSGJ","schema_version":"1.0","canonical_sha256":"d0773348c96ab8dc7882a98c09f97d6f8dad7d26dcbd94162e2809c123fd878f","source":{"kind":"arxiv","id":"2306.00307","version":3},"attestation_state":"computed","paper":{"title":"A Mini-Batch Method for Solving Nonlinear PDEs with Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Houman Owhadi, Xianjin Yang","submitted_at":"2023-06-01T03:10:13Z","abstract_excerpt":"Gaussian processes (GPs) based methods for solving partial differential equations (PDEs) demonstrate great promise by bridging the gap between the theoretical rigor of traditional numerical algorithms and the flexible design of machine learning solvers. The main bottleneck of GP methods lies in the inversion of a covariance matrix, whose cost grows cubically concerning the size of samples. Drawing inspiration from neural networks, we propose a mini-batch algorithm combined with GPs to solve nonlinear PDEs. A naive deployment of a stochastic gradient descent method for solving PDEs with GPs is "},"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":"2306.00307","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2023-06-01T03:10:13Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"9e74a635901f201515e8c92870890df104e23622bc1e5e8bf7fdaff16229def7","abstract_canon_sha256":"c5177c7eb6a3084dab8efe791f2e3dedf694e40c0f54a984e626c22017cbbe74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:59.150359Z","signature_b64":"JVAYnVDNkJ7vQVlluDpfgX3aepux4/L3FXkBJW2o05Ml783dIXEFmQncf454YMbso9jyz5ZOm6NVrzMFmT16Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0773348c96ab8dc7882a98c09f97d6f8dad7d26dcbd94162e2809c123fd878f","last_reissued_at":"2026-07-05T07:39:59.149950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:59.149950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mini-Batch Method for Solving Nonlinear PDEs with Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Houman Owhadi, Xianjin Yang","submitted_at":"2023-06-01T03:10:13Z","abstract_excerpt":"Gaussian processes (GPs) based methods for solving partial differential equations (PDEs) demonstrate great promise by bridging the gap between the theoretical rigor of traditional numerical algorithms and the flexible design of machine learning solvers. The main bottleneck of GP methods lies in the inversion of a covariance matrix, whose cost grows cubically concerning the size of samples. Drawing inspiration from neural networks, we propose a mini-batch algorithm combined with GPs to solve nonlinear PDEs. A naive deployment of a stochastic gradient descent method for solving PDEs with GPs is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00307","kind":"arxiv","version":3},"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/2306.00307/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":"2306.00307","created_at":"2026-07-05T07:39:59.150002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00307v3","created_at":"2026-07-05T07:39:59.150002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00307","created_at":"2026-07-05T07:39:59.150002+00:00"},{"alias_kind":"pith_short_12","alias_value":"2B3TGSGJNK4N","created_at":"2026-07-05T07:39:59.150002+00:00"},{"alias_kind":"pith_short_16","alias_value":"2B3TGSGJNK4NY6EC","created_at":"2026-07-05T07:39:59.150002+00:00"},{"alias_kind":"pith_short_8","alias_value":"2B3TGSGJ","created_at":"2026-07-05T07:39:59.150002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.07765","citing_title":"Solving Nonlinear PDEs with Sparse Radial Basis Function Networks","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6","json":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6.json","graph_json":"https://pith.science/api/pith-number/2B3TGSGJNK4NY6ECVGGAT6L5N6/graph.json","events_json":"https://pith.science/api/pith-number/2B3TGSGJNK4NY6ECVGGAT6L5N6/events.json","paper":"https://pith.science/paper/2B3TGSGJ"},"agent_actions":{"view_html":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6","download_json":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6.json","view_paper":"https://pith.science/paper/2B3TGSGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00307&json=true","fetch_graph":"https://pith.science/api/pith-number/2B3TGSGJNK4NY6ECVGGAT6L5N6/graph.json","fetch_events":"https://pith.science/api/pith-number/2B3TGSGJNK4NY6ECVGGAT6L5N6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6/action/storage_attestation","attest_author":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6/action/author_attestation","sign_citation":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6/action/citation_signature","submit_replication":"https://pith.science/pith/2B3TGSGJNK4NY6ECVGGAT6L5N6/action/replication_record"}},"created_at":"2026-07-05T07:39:59.150002+00:00","updated_at":"2026-07-05T07:39:59.150002+00:00"}