{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H3YR6JVAWSNETQ2JN4ENPJP66E","short_pith_number":"pith:H3YR6JVA","schema_version":"1.0","canonical_sha256":"3ef11f26a0b49a49c3496f08d7a5fef10e32e84a1cf851eeb1ce2b860466a75c","source":{"kind":"arxiv","id":"2103.00542","version":6},"attestation_state":"computed","paper":{"title":"Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on H\\\"older Class","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Fengru Wang, Jerry Zhijian Yang, Xiliang Lu, Yanming Lai, Yuanyuan Yang, Yuling Jiao","submitted_at":"2021-02-28T15:57:42Z","abstract_excerpt":"In this paper, we construct neural networks with ReLU, sine and $2^x$ as activation functions. For general continuous $f$ defined on $[0,1]^d$ with continuity modulus $\\omega_f(\\cdot)$, we construct ReLU-sine-$2^x$ networks that enjoy an approximation rate $\\mathcal{O}(\\omega_f(\\sqrt{d})\\cdot2^{-M}+\\omega_{f}\\left(\\frac{\\sqrt{d}}{N}\\right))$, where $M,N\\in \\mathbb{N}^{+}$ denote the hyperparameters related to widths of the networks. As a consequence, we can construct ReLU-sine-$2^x$ network with the depth $5$ and width $\\max\\left\\{\\left\\lceil2d^{3/2}\\left(\\frac{3\\mu}{\\epsilon}\\right)^{1/{\\alph"},"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":"2103.00542","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-28T15:57:42Z","cross_cats_sorted":["cs.NA","cs.NE","math.NA"],"title_canon_sha256":"672b759af7ab34fa899c332230c1915af7285c5ce5c156f10cbdf01caab91807","abstract_canon_sha256":"bf4e8a64f1e226534203edda036f3cef6872ca718f0f01cbc08020272a898e02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:06.622905Z","signature_b64":"L8zuaQ9Sy1LSQKNk+kB7zpswlZG8AwH/ezidUsrUAHtcH0kL/TjklFr/Yj+phKgSxa5rQUAi5gB+mhcki/BKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ef11f26a0b49a49c3496f08d7a5fef10e32e84a1cf851eeb1ce2b860466a75c","last_reissued_at":"2026-07-05T04:48:06.622341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:06.622341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on H\\\"older Class","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","cs.NE","math.NA"],"primary_cat":"cs.LG","authors_text":"Fengru Wang, Jerry Zhijian Yang, Xiliang Lu, Yanming Lai, Yuanyuan Yang, Yuling Jiao","submitted_at":"2021-02-28T15:57:42Z","abstract_excerpt":"In this paper, we construct neural networks with ReLU, sine and $2^x$ as activation functions. For general continuous $f$ defined on $[0,1]^d$ with continuity modulus $\\omega_f(\\cdot)$, we construct ReLU-sine-$2^x$ networks that enjoy an approximation rate $\\mathcal{O}(\\omega_f(\\sqrt{d})\\cdot2^{-M}+\\omega_{f}\\left(\\frac{\\sqrt{d}}{N}\\right))$, where $M,N\\in \\mathbb{N}^{+}$ denote the hyperparameters related to widths of the networks. As a consequence, we can construct ReLU-sine-$2^x$ network with the depth $5$ and width $\\max\\left\\{\\left\\lceil2d^{3/2}\\left(\\frac{3\\mu}{\\epsilon}\\right)^{1/{\\alph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00542","kind":"arxiv","version":6},"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/2103.00542/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":"2103.00542","created_at":"2026-07-05T04:48:06.622401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00542v6","created_at":"2026-07-05T04:48:06.622401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00542","created_at":"2026-07-05T04:48:06.622401+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3YR6JVAWSNE","created_at":"2026-07-05T04:48:06.622401+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3YR6JVAWSNETQ2J","created_at":"2026-07-05T04:48:06.622401+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3YR6JVA","created_at":"2026-07-05T04:48:06.622401+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/H3YR6JVAWSNETQ2JN4ENPJP66E","json":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E.json","graph_json":"https://pith.science/api/pith-number/H3YR6JVAWSNETQ2JN4ENPJP66E/graph.json","events_json":"https://pith.science/api/pith-number/H3YR6JVAWSNETQ2JN4ENPJP66E/events.json","paper":"https://pith.science/paper/H3YR6JVA"},"agent_actions":{"view_html":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E","download_json":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E.json","view_paper":"https://pith.science/paper/H3YR6JVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00542&json=true","fetch_graph":"https://pith.science/api/pith-number/H3YR6JVAWSNETQ2JN4ENPJP66E/graph.json","fetch_events":"https://pith.science/api/pith-number/H3YR6JVAWSNETQ2JN4ENPJP66E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E/action/storage_attestation","attest_author":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E/action/author_attestation","sign_citation":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E/action/citation_signature","submit_replication":"https://pith.science/pith/H3YR6JVAWSNETQ2JN4ENPJP66E/action/replication_record"}},"created_at":"2026-07-05T04:48:06.622401+00:00","updated_at":"2026-07-05T04:48:06.622401+00:00"}