{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FLLFMEBBLP6SPLFQC6WWDNGXH5","short_pith_number":"pith:FLLFMEBB","schema_version":"1.0","canonical_sha256":"2ad65610215bfd27acb017ad61b4d73f662db0ebc596cd7c0d6bcc98a174c5ef","source":{"kind":"arxiv","id":"1607.07819","version":3},"attestation_state":"computed","paper":{"title":"Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ \\ell^1 $ and $ \\ell^0 $ Controls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrew R. Barron, Jason M. Klusowski","submitted_at":"2016-07-26T17:52:00Z","abstract_excerpt":"We establish $ L^{\\infty} $ and $ L^2 $ error bounds for functions of many variables that are approximated by linear combinations of ReLU (rectified linear unit) and squared ReLU ridge functions with $ \\ell^1 $ and $ \\ell^0 $ controls on their inner and outer parameters. With the squared ReLU ridge function, we show that the $ L^2 $ approximation error is inversely proportional to the inner layer $ \\ell^0 $ sparsity and it need only be sublinear in the outer layer $ \\ell^0 $ sparsity. Our constructions are obtained using a variant of the Jones-Barron probabilistic method, which can be interpre"},"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":"1607.07819","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-26T17:52:00Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"7bf31ae179baa81fc3790b6e665653d678fd6c5e2e47e0f7f11368229dcbbef4","abstract_canon_sha256":"43f693ba992312314b38de34f763959be2b6d714c3340f19ff4cb284764772d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:05.740333Z","signature_b64":"DNAeB0phOx7s86lMX7Gtj5K48yZKsOSmprGPhrnWlz9H0XUXh5C84f5aWG8YuVIifu6fqnS+n7kLnQUzARJLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad65610215bfd27acb017ad61b4d73f662db0ebc596cd7c0d6bcc98a174c5ef","last_reissued_at":"2026-05-18T00:15:05.739784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:05.739784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ \\ell^1 $ and $ \\ell^0 $ Controls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrew R. Barron, Jason M. Klusowski","submitted_at":"2016-07-26T17:52:00Z","abstract_excerpt":"We establish $ L^{\\infty} $ and $ L^2 $ error bounds for functions of many variables that are approximated by linear combinations of ReLU (rectified linear unit) and squared ReLU ridge functions with $ \\ell^1 $ and $ \\ell^0 $ controls on their inner and outer parameters. With the squared ReLU ridge function, we show that the $ L^2 $ approximation error is inversely proportional to the inner layer $ \\ell^0 $ sparsity and it need only be sublinear in the outer layer $ \\ell^0 $ sparsity. Our constructions are obtained using a variant of the Jones-Barron probabilistic method, which can be interpre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.07819","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":""},"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":"1607.07819","created_at":"2026-05-18T00:15:05.739870+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.07819v3","created_at":"2026-05-18T00:15:05.739870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.07819","created_at":"2026-05-18T00:15:05.739870+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLLFMEBBLP6S","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLLFMEBBLP6SPLFQ","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLLFMEBB","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.04895","citing_title":"Super-resolution meets machine learning: approximation of measures","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08869","citing_title":"Adaptive Randomized Neural Networks with Locally Activation Function: Theory and Algorithm for Solving PDEs","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5","json":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5.json","graph_json":"https://pith.science/api/pith-number/FLLFMEBBLP6SPLFQC6WWDNGXH5/graph.json","events_json":"https://pith.science/api/pith-number/FLLFMEBBLP6SPLFQC6WWDNGXH5/events.json","paper":"https://pith.science/paper/FLLFMEBB"},"agent_actions":{"view_html":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5","download_json":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5.json","view_paper":"https://pith.science/paper/FLLFMEBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.07819&json=true","fetch_graph":"https://pith.science/api/pith-number/FLLFMEBBLP6SPLFQC6WWDNGXH5/graph.json","fetch_events":"https://pith.science/api/pith-number/FLLFMEBBLP6SPLFQC6WWDNGXH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5/action/storage_attestation","attest_author":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5/action/author_attestation","sign_citation":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5/action/citation_signature","submit_replication":"https://pith.science/pith/FLLFMEBBLP6SPLFQC6WWDNGXH5/action/replication_record"}},"created_at":"2026-05-18T00:15:05.739870+00:00","updated_at":"2026-05-18T00:15:05.739870+00:00"}