{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LAK3ZVV2NDWR4CXXDAEZDJGNYI","short_pith_number":"pith:LAK3ZVV2","schema_version":"1.0","canonical_sha256":"5815bcd6ba68ed1e0af7180991a4cdc2324d6e0afe5ac31052d09754bd39deed","source":{"kind":"arxiv","id":"2605.31152","version":1},"attestation_state":"computed","paper":{"title":"Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Jun Fan, Yunfei Yang","submitted_at":"2026-05-29T11:04:06Z","abstract_excerpt":"This paper studies how efficiently deep ReLU neural networks can approximate and learn smooth functions. When the error is measured in $L^p([0,1]^d)$ norm and the approximator is a network with width $W$ and depth $L$, recent works have proven the supper approximation rate $\\mathcal{O}((WL)^{-2s/d})$ for Besov space $\\mathcal{B}^s_{q,r}([0,1]^d)$ under the Sobolev embedding condition $s/d>1/q-1/p$. In order to overcome the curse of dimensionality in this rate, we extent this result to anisotropic and mixed smooth function classes. We establish the approximation rate $\\mathcal{O}((WL)^{-2\\tilde"},"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":"2605.31152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-29T11:04:06Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"e86fb9efdc5a30fd4a82d6962bb2d643d14c2bc3f8270ac7ff55851e13d4d608","abstract_canon_sha256":"0680d7488cd8c07abac422282282d616a34272ccb673e87dc040dab087fcd88a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:01.427295Z","signature_b64":"2gUiKLkiXFJi5WPUOECNw4AbzXPRacoZZbYJyTyAVdkP5ExAp4PKR40j8Ywzt4YX7jSgHg2rJuPSHIEhaf0TDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5815bcd6ba68ed1e0af7180991a4cdc2324d6e0afe5ac31052d09754bd39deed","last_reissued_at":"2026-06-01T01:04:01.426720Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:01.426720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Jun Fan, Yunfei Yang","submitted_at":"2026-05-29T11:04:06Z","abstract_excerpt":"This paper studies how efficiently deep ReLU neural networks can approximate and learn smooth functions. When the error is measured in $L^p([0,1]^d)$ norm and the approximator is a network with width $W$ and depth $L$, recent works have proven the supper approximation rate $\\mathcal{O}((WL)^{-2s/d})$ for Besov space $\\mathcal{B}^s_{q,r}([0,1]^d)$ under the Sobolev embedding condition $s/d>1/q-1/p$. In order to overcome the curse of dimensionality in this rate, we extent this result to anisotropic and mixed smooth function classes. We establish the approximation rate $\\mathcal{O}((WL)^{-2\\tilde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31152","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/2605.31152/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":"2605.31152","created_at":"2026-06-01T01:04:01.426810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31152v1","created_at":"2026-06-01T01:04:01.426810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31152","created_at":"2026-06-01T01:04:01.426810+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAK3ZVV2NDWR","created_at":"2026-06-01T01:04:01.426810+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAK3ZVV2NDWR4CXX","created_at":"2026-06-01T01:04:01.426810+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAK3ZVV2","created_at":"2026-06-01T01:04:01.426810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI","json":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI.json","graph_json":"https://pith.science/api/pith-number/LAK3ZVV2NDWR4CXXDAEZDJGNYI/graph.json","events_json":"https://pith.science/api/pith-number/LAK3ZVV2NDWR4CXXDAEZDJGNYI/events.json","paper":"https://pith.science/paper/LAK3ZVV2"},"agent_actions":{"view_html":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI","download_json":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI.json","view_paper":"https://pith.science/paper/LAK3ZVV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31152&json=true","fetch_graph":"https://pith.science/api/pith-number/LAK3ZVV2NDWR4CXXDAEZDJGNYI/graph.json","fetch_events":"https://pith.science/api/pith-number/LAK3ZVV2NDWR4CXXDAEZDJGNYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI/action/storage_attestation","attest_author":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI/action/author_attestation","sign_citation":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI/action/citation_signature","submit_replication":"https://pith.science/pith/LAK3ZVV2NDWR4CXXDAEZDJGNYI/action/replication_record"}},"created_at":"2026-06-01T01:04:01.426810+00:00","updated_at":"2026-06-01T01:04:01.426810+00:00"}