{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:M34LAQOF66ZW663VSWAYKR3FWL","short_pith_number":"pith:M34LAQOF","schema_version":"1.0","canonical_sha256":"66f8b041c5f7b36f7b759581854765b2d74b12602184f05f9a67c6bd13f054bc","source":{"kind":"arxiv","id":"1706.02410","version":2},"attestation_state":"computed","paper":{"title":"Convergence rates of least squares regression estimators with heavy-tailed errors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Jon A. Wellner, Qiyang Han","submitted_at":"2017-06-07T23:25:29Z","abstract_excerpt":"We study the performance of the Least Squares Estimator (LSE) in a general nonparametric regression model, when the errors are independent of the covariates but may only have a $p$-th moment ($p\\geq 1$). In such a heavy-tailed regression setting, we show that if the model satisfies a standard `entropy condition' with exponent $\\alpha \\in (0,2)$, then the $L_2$ loss of the LSE converges at a rate \\begin{align*} \\mathcal{O}_{\\mathbf{P}}\\big(n^{-\\frac{1}{2+\\alpha}} \\vee n^{-\\frac{1}{2}+\\frac{1}{2p}}\\big). \\end{align*} Such a rate cannot be improved under the entropy condition alone.\n  This rate q"},"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":"1706.02410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-06-07T23:25:29Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"68f0e20a314c1411bdd6da474dbdb9afe7c0eb7e82031084d433fc1f76f24446","abstract_canon_sha256":"701a7782b4c55f90cfe55b29728232c74e12563fa5004a8a0de7eaefc135656d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:47.712885Z","signature_b64":"tljUyw6pMm19OwhE1idtnwKL3c3MbfPWyCAvfZOBjBIqUO0LRqM/pSmTSVSNSgEq/6kLE0kVj9NEBeWKMCoDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66f8b041c5f7b36f7b759581854765b2d74b12602184f05f9a67c6bd13f054bc","last_reissued_at":"2026-05-18T00:10:47.712308Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:47.712308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence rates of least squares regression estimators with heavy-tailed errors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Jon A. Wellner, Qiyang Han","submitted_at":"2017-06-07T23:25:29Z","abstract_excerpt":"We study the performance of the Least Squares Estimator (LSE) in a general nonparametric regression model, when the errors are independent of the covariates but may only have a $p$-th moment ($p\\geq 1$). In such a heavy-tailed regression setting, we show that if the model satisfies a standard `entropy condition' with exponent $\\alpha \\in (0,2)$, then the $L_2$ loss of the LSE converges at a rate \\begin{align*} \\mathcal{O}_{\\mathbf{P}}\\big(n^{-\\frac{1}{2+\\alpha}} \\vee n^{-\\frac{1}{2}+\\frac{1}{2p}}\\big). \\end{align*} Such a rate cannot be improved under the entropy condition alone.\n  This rate q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.02410","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":""},"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":"1706.02410","created_at":"2026-05-18T00:10:47.712423+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.02410v2","created_at":"2026-05-18T00:10:47.712423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.02410","created_at":"2026-05-18T00:10:47.712423+00:00"},{"alias_kind":"pith_short_12","alias_value":"M34LAQOF66ZW","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"M34LAQOF66ZW663V","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"M34LAQOF","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.02088","citing_title":"On Least Squares Estimation under Heteroscedastic and Heavy-Tailed Errors","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL","json":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL.json","graph_json":"https://pith.science/api/pith-number/M34LAQOF66ZW663VSWAYKR3FWL/graph.json","events_json":"https://pith.science/api/pith-number/M34LAQOF66ZW663VSWAYKR3FWL/events.json","paper":"https://pith.science/paper/M34LAQOF"},"agent_actions":{"view_html":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL","download_json":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL.json","view_paper":"https://pith.science/paper/M34LAQOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.02410&json=true","fetch_graph":"https://pith.science/api/pith-number/M34LAQOF66ZW663VSWAYKR3FWL/graph.json","fetch_events":"https://pith.science/api/pith-number/M34LAQOF66ZW663VSWAYKR3FWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL/action/storage_attestation","attest_author":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL/action/author_attestation","sign_citation":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL/action/citation_signature","submit_replication":"https://pith.science/pith/M34LAQOF66ZW663VSWAYKR3FWL/action/replication_record"}},"created_at":"2026-05-18T00:10:47.712423+00:00","updated_at":"2026-05-18T00:10:47.712423+00:00"}