{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M36Q2K6G5TROWQJ5X2VNVJUTPU","short_pith_number":"pith:M36Q2K6G","schema_version":"1.0","canonical_sha256":"66fd0d2bc6ece2eb413dbeaadaa6937d14174e8547d565910b64220027180aaa","source":{"kind":"arxiv","id":"2203.09659","version":4},"attestation_state":"computed","paper":{"title":"Low-degree learning and the metric entropy of polynomials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","math.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandros Eskenazis, Lauritz Streck, Paata Ivanisvili","submitted_at":"2022-03-17T23:52:08Z","abstract_excerpt":"Let $\\mathscr{F}_{n,d}$ be the class of all functions $f:\\{-1,1\\}^n\\to[-1,1]$ on the $n$-dimensional discrete hypercube of degree at most $d$. In the first part of this paper, we prove that any (deterministic or randomized) algorithm which learns $\\mathscr{F}_{n,d}$ with $L_2$-accuracy $\\varepsilon$ requires at least $\\Omega((1-\\sqrt{\\varepsilon})2^d\\log n)$ queries for large enough $n$, thus establishing the sharpness as $n\\to\\infty$ of a recent upper bound of Eskenazis and Ivanisvili (2021). To do this, we show that the $L_2$-packing numbers $\\mathsf{M}(\\mathscr{F}_{n,d},\\|\\cdot\\|_{L_2},\\var"},"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":"2203.09659","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T23:52:08Z","cross_cats_sorted":["cs.CC","math.CO","stat.ML"],"title_canon_sha256":"565b9ba35f387d6e29e0a4af4e9929b648d358a3c191ef9660c3827a8fd053cb","abstract_canon_sha256":"186513531f1563d5ddb4beae870f63bc1da96b679a842c965956bbf58ce9e6f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:32.461343Z","signature_b64":"4hUK9ZEut6fQeVlA8+3UE6fqaXDqfIH9InqOEYciYC9WjFalcgpM6g9mWrk9dLIAQ/d2hGXmJehOnk1LCy8OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66fd0d2bc6ece2eb413dbeaadaa6937d14174e8547d565910b64220027180aaa","last_reissued_at":"2026-07-05T09:23:32.460885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:32.460885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-degree learning and the metric entropy of polynomials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","math.CO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandros Eskenazis, Lauritz Streck, Paata Ivanisvili","submitted_at":"2022-03-17T23:52:08Z","abstract_excerpt":"Let $\\mathscr{F}_{n,d}$ be the class of all functions $f:\\{-1,1\\}^n\\to[-1,1]$ on the $n$-dimensional discrete hypercube of degree at most $d$. In the first part of this paper, we prove that any (deterministic or randomized) algorithm which learns $\\mathscr{F}_{n,d}$ with $L_2$-accuracy $\\varepsilon$ requires at least $\\Omega((1-\\sqrt{\\varepsilon})2^d\\log n)$ queries for large enough $n$, thus establishing the sharpness as $n\\to\\infty$ of a recent upper bound of Eskenazis and Ivanisvili (2021). To do this, we show that the $L_2$-packing numbers $\\mathsf{M}(\\mathscr{F}_{n,d},\\|\\cdot\\|_{L_2},\\var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09659","kind":"arxiv","version":4},"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/2203.09659/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":"2203.09659","created_at":"2026-07-05T09:23:32.460945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09659v4","created_at":"2026-07-05T09:23:32.460945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09659","created_at":"2026-07-05T09:23:32.460945+00:00"},{"alias_kind":"pith_short_12","alias_value":"M36Q2K6G5TRO","created_at":"2026-07-05T09:23:32.460945+00:00"},{"alias_kind":"pith_short_16","alias_value":"M36Q2K6G5TROWQJ5","created_at":"2026-07-05T09:23:32.460945+00:00"},{"alias_kind":"pith_short_8","alias_value":"M36Q2K6G","created_at":"2026-07-05T09:23:32.460945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10355","citing_title":"Entropy and Learning of Lipschitz Functions under Log-Concave Measures","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU","json":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU.json","graph_json":"https://pith.science/api/pith-number/M36Q2K6G5TROWQJ5X2VNVJUTPU/graph.json","events_json":"https://pith.science/api/pith-number/M36Q2K6G5TROWQJ5X2VNVJUTPU/events.json","paper":"https://pith.science/paper/M36Q2K6G"},"agent_actions":{"view_html":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU","download_json":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU.json","view_paper":"https://pith.science/paper/M36Q2K6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09659&json=true","fetch_graph":"https://pith.science/api/pith-number/M36Q2K6G5TROWQJ5X2VNVJUTPU/graph.json","fetch_events":"https://pith.science/api/pith-number/M36Q2K6G5TROWQJ5X2VNVJUTPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU/action/storage_attestation","attest_author":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU/action/author_attestation","sign_citation":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU/action/citation_signature","submit_replication":"https://pith.science/pith/M36Q2K6G5TROWQJ5X2VNVJUTPU/action/replication_record"}},"created_at":"2026-07-05T09:23:32.460945+00:00","updated_at":"2026-07-05T09:23:32.460945+00:00"}