{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JAGXJBTYPMY2JWCBWDCESKCBNX","short_pith_number":"pith:JAGXJBTY","schema_version":"1.0","canonical_sha256":"480d7486787b31a4d841b0c44928416df9271d5af4b6277fa3735e84070453db","source":{"kind":"arxiv","id":"2305.05642","version":3},"attestation_state":"computed","paper":{"title":"A duality framework for analyzing random feature and two-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hongrui Chen, Jihao Long, Lei Wu","submitted_at":"2023-05-09T17:41:50Z","abstract_excerpt":"We consider the problem of learning functions within the $\\mathcal{F}_{p,\\pi}$ and Barron spaces, which play crucial roles in understanding random feature models (RFMs), two-layer neural networks, as well as kernel methods. Leveraging tools from information-based complexity (IBC), we establish a dual equivalence between approximation and estimation, and then apply it to study the learning of the preceding function spaces. The duality allows us to focus on the more tractable problem between approximation and estimation. To showcase the efficacy of our duality framework, we delve into two import"},"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":"2305.05642","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-09T17:41:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"43449d186cb62259841f075de42c849bb593123d660ecec661f1aa75098e131f","abstract_canon_sha256":"bdbf565da3dc3b7f69bc24cac523edace5c11589779af5e04ef083fb230a84e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:12.767750Z","signature_b64":"03UXcgqyFLciK/jwA1pfPKSC1d/FrujMtFZaRYKpqVaUj5EC+cbbj2UemIdoxCz5xNyI1IiY2iMJQUglsuD0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"480d7486787b31a4d841b0c44928416df9271d5af4b6277fa3735e84070453db","last_reissued_at":"2026-07-05T10:12:12.767360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:12.767360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A duality framework for analyzing random feature and two-layer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hongrui Chen, Jihao Long, Lei Wu","submitted_at":"2023-05-09T17:41:50Z","abstract_excerpt":"We consider the problem of learning functions within the $\\mathcal{F}_{p,\\pi}$ and Barron spaces, which play crucial roles in understanding random feature models (RFMs), two-layer neural networks, as well as kernel methods. Leveraging tools from information-based complexity (IBC), we establish a dual equivalence between approximation and estimation, and then apply it to study the learning of the preceding function spaces. The duality allows us to focus on the more tractable problem between approximation and estimation. To showcase the efficacy of our duality framework, we delve into two import"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05642","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/2305.05642/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":"2305.05642","created_at":"2026-07-05T10:12:12.767414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05642v3","created_at":"2026-07-05T10:12:12.767414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05642","created_at":"2026-07-05T10:12:12.767414+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAGXJBTYPMY2","created_at":"2026-07-05T10:12:12.767414+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAGXJBTYPMY2JWCB","created_at":"2026-07-05T10:12:12.767414+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAGXJBTY","created_at":"2026-07-05T10:12:12.767414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07371","citing_title":"Spectral connvergece of random feature method in one dimension","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX","json":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX.json","graph_json":"https://pith.science/api/pith-number/JAGXJBTYPMY2JWCBWDCESKCBNX/graph.json","events_json":"https://pith.science/api/pith-number/JAGXJBTYPMY2JWCBWDCESKCBNX/events.json","paper":"https://pith.science/paper/JAGXJBTY"},"agent_actions":{"view_html":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX","download_json":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX.json","view_paper":"https://pith.science/paper/JAGXJBTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05642&json=true","fetch_graph":"https://pith.science/api/pith-number/JAGXJBTYPMY2JWCBWDCESKCBNX/graph.json","fetch_events":"https://pith.science/api/pith-number/JAGXJBTYPMY2JWCBWDCESKCBNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX/action/storage_attestation","attest_author":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX/action/author_attestation","sign_citation":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX/action/citation_signature","submit_replication":"https://pith.science/pith/JAGXJBTYPMY2JWCBWDCESKCBNX/action/replication_record"}},"created_at":"2026-07-05T10:12:12.767414+00:00","updated_at":"2026-07-05T10:12:12.767414+00:00"}