{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L5OUG4ORBDJYD66UEB3DJ7VFDY","short_pith_number":"pith:L5OUG4OR","schema_version":"1.0","canonical_sha256":"5f5d4371d108d381fbd4207634fea51e00d8cd9f58ffa8f4365755b0603352cc","source":{"kind":"arxiv","id":"2303.02255","version":2},"attestation_state":"computed","paper":{"title":"Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Difan Zou, Jingfeng Wu, Quanquan Gu, Sham M. Kakade, Vladimir Braverman, Zixiang Chen","submitted_at":"2023-03-03T23:02:23Z","abstract_excerpt":"This paper considers the problem of learning a single ReLU neuron with squared loss (a.k.a., ReLU regression) in the overparameterized regime, where the input dimension can exceed the number of samples. We analyze a Perceptron-type algorithm called GLM-tron (Kakade et al., 2011) and provide its dimension-free risk upper bounds for high-dimensional ReLU regression in both well-specified and misspecified settings. Our risk bounds recover several existing results as special cases. Moreover, in the well-specified setting, we provide an instance-wise matching risk lower bound for GLM-tron. Our uppe"},"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":"2303.02255","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T23:02:23Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"eed2d066178c36f5238b6967d6c55368d1b7e07060d1920179eb15f70cb3058c","abstract_canon_sha256":"769a88cc552734de445ef3f8c55ec05c033533643840e9de5d0a21fc40a0f106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:28.510998Z","signature_b64":"vdWu/cDRYpzw1SHwhcI01aXQZTyPQiAVBPBSuBr/7QKB6+zhnPgIOlb2L29zc9HbNdHZrhh7aizw7uy5CnCBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f5d4371d108d381fbd4207634fea51e00d8cd9f58ffa8f4365755b0603352cc","last_reissued_at":"2026-07-05T06:24:28.510625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:28.510625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Difan Zou, Jingfeng Wu, Quanquan Gu, Sham M. Kakade, Vladimir Braverman, Zixiang Chen","submitted_at":"2023-03-03T23:02:23Z","abstract_excerpt":"This paper considers the problem of learning a single ReLU neuron with squared loss (a.k.a., ReLU regression) in the overparameterized regime, where the input dimension can exceed the number of samples. We analyze a Perceptron-type algorithm called GLM-tron (Kakade et al., 2011) and provide its dimension-free risk upper bounds for high-dimensional ReLU regression in both well-specified and misspecified settings. Our risk bounds recover several existing results as special cases. Moreover, in the well-specified setting, we provide an instance-wise matching risk lower bound for GLM-tron. Our uppe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02255","kind":"arxiv","version":2},"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/2303.02255/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":"2303.02255","created_at":"2026-07-05T06:24:28.510681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02255v2","created_at":"2026-07-05T06:24:28.510681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02255","created_at":"2026-07-05T06:24:28.510681+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5OUG4ORBDJY","created_at":"2026-07-05T06:24:28.510681+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5OUG4ORBDJYD66U","created_at":"2026-07-05T06:24:28.510681+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5OUG4OR","created_at":"2026-07-05T06:24:28.510681+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/L5OUG4ORBDJYD66UEB3DJ7VFDY","json":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY.json","graph_json":"https://pith.science/api/pith-number/L5OUG4ORBDJYD66UEB3DJ7VFDY/graph.json","events_json":"https://pith.science/api/pith-number/L5OUG4ORBDJYD66UEB3DJ7VFDY/events.json","paper":"https://pith.science/paper/L5OUG4OR"},"agent_actions":{"view_html":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY","download_json":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY.json","view_paper":"https://pith.science/paper/L5OUG4OR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02255&json=true","fetch_graph":"https://pith.science/api/pith-number/L5OUG4ORBDJYD66UEB3DJ7VFDY/graph.json","fetch_events":"https://pith.science/api/pith-number/L5OUG4ORBDJYD66UEB3DJ7VFDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY/action/storage_attestation","attest_author":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY/action/author_attestation","sign_citation":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY/action/citation_signature","submit_replication":"https://pith.science/pith/L5OUG4ORBDJYD66UEB3DJ7VFDY/action/replication_record"}},"created_at":"2026-07-05T06:24:28.510681+00:00","updated_at":"2026-07-05T06:24:28.510681+00:00"}