{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6CASU6QV6HOOD7GDU6YK2LO6U2","short_pith_number":"pith:6CASU6QV","schema_version":"1.0","canonical_sha256":"f0812a7a15f1dce1fcc3a7b0ad2ddea6839ae23880c3067b036a54b36d26a461","source":{"kind":"arxiv","id":"2102.04401","version":1},"attestation_state":"computed","paper":{"title":"The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas, Nikos Zarifis, Thanasis Pittas","submitted_at":"2021-02-08T18:06:32Z","abstract_excerpt":"We study the problem of agnostic learning under the Gaussian distribution. We develop a method for finding hard families of examples for a wide class of problems by using LP duality. For Boolean-valued concept classes, we show that the $L^1$-regression algorithm is essentially best possible, and therefore that the computational difficulty of agnostically learning a concept class is closely related to the polynomial degree required to approximate any function from the class in $L^1$-norm. Using this characterization along with additional analytic tools, we obtain optimal SQ lower bounds for agn"},"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":"2102.04401","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-08T18:06:32Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"70eeb1e2705e0dd88de94529333eb6ffa6abdcc09505af38b66f95d2734b4086","abstract_canon_sha256":"b1f69f622e4322360d22d30979e47d1b268c32432f45fb8f10e1a74b142ce62b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:32.893086Z","signature_b64":"gFFgO3fh3fLXh9EEmSQG+7FZV+1nKiVGEf08unw3qZ2Hf9nWwJw4u3pMTFpQWKA97yf2Erd8jW69QB1km+DhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0812a7a15f1dce1fcc3a7b0ad2ddea6839ae23880c3067b036a54b36d26a461","last_reissued_at":"2026-07-05T02:13:32.892639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:32.892639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas, Nikos Zarifis, Thanasis Pittas","submitted_at":"2021-02-08T18:06:32Z","abstract_excerpt":"We study the problem of agnostic learning under the Gaussian distribution. We develop a method for finding hard families of examples for a wide class of problems by using LP duality. For Boolean-valued concept classes, we show that the $L^1$-regression algorithm is essentially best possible, and therefore that the computational difficulty of agnostically learning a concept class is closely related to the polynomial degree required to approximate any function from the class in $L^1$-norm. Using this characterization along with additional analytic tools, we obtain optimal SQ lower bounds for agn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04401","kind":"arxiv","version":1},"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/2102.04401/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":"2102.04401","created_at":"2026-07-05T02:13:32.892692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04401v1","created_at":"2026-07-05T02:13:32.892692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04401","created_at":"2026-07-05T02:13:32.892692+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CASU6QV6HOO","created_at":"2026-07-05T02:13:32.892692+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CASU6QV6HOOD7GD","created_at":"2026-07-05T02:13:32.892692+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CASU6QV","created_at":"2026-07-05T02:13:32.892692+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/6CASU6QV6HOOD7GDU6YK2LO6U2","json":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2.json","graph_json":"https://pith.science/api/pith-number/6CASU6QV6HOOD7GDU6YK2LO6U2/graph.json","events_json":"https://pith.science/api/pith-number/6CASU6QV6HOOD7GDU6YK2LO6U2/events.json","paper":"https://pith.science/paper/6CASU6QV"},"agent_actions":{"view_html":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2","download_json":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2.json","view_paper":"https://pith.science/paper/6CASU6QV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04401&json=true","fetch_graph":"https://pith.science/api/pith-number/6CASU6QV6HOOD7GDU6YK2LO6U2/graph.json","fetch_events":"https://pith.science/api/pith-number/6CASU6QV6HOOD7GDU6YK2LO6U2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2/action/storage_attestation","attest_author":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2/action/author_attestation","sign_citation":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2/action/citation_signature","submit_replication":"https://pith.science/pith/6CASU6QV6HOOD7GDU6YK2LO6U2/action/replication_record"}},"created_at":"2026-07-05T02:13:32.892692+00:00","updated_at":"2026-07-05T02:13:32.892692+00:00"}