{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AZVQ6XJTONTIMY4QFZRA6LINNM","short_pith_number":"pith:AZVQ6XJT","schema_version":"1.0","canonical_sha256":"066b0f5d3373668663902e620f2d0d6b24cdf3a41c540a078578618a38831ddc","source":{"kind":"arxiv","id":"2310.06289","version":2},"attestation_state":"computed","paper":{"title":"Better and Simpler Lower Bounds for Differentially Private Statistical Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS","cs.IT","cs.LG","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Shyam Narayanan","submitted_at":"2023-10-10T04:02:43Z","abstract_excerpt":"We provide optimal lower bounds for two well-known parameter estimation (also known as statistical estimation) tasks in high dimensions with approximate differential privacy. First, we prove that for any $\\alpha \\le O(1)$, estimating the covariance of a Gaussian up to spectral error $\\alpha$ requires $\\tilde{\\Omega}\\left(\\frac{d^{3/2}}{\\alpha \\varepsilon} + \\frac{d}{\\alpha^2}\\right)$ samples, which is tight up to logarithmic factors. This result improves over previous work which established this for $\\alpha \\le O\\left(\\frac{1}{\\sqrt{d}}\\right)$, and is also simpler than previous work. Next, we"},"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":"2310.06289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-10-10T04:02:43Z","cross_cats_sorted":["cs.CR","cs.DS","cs.IT","cs.LG","math.IT","stat.TH"],"title_canon_sha256":"2a275678b3e9cb26a0f532b57041a4dd76ee30ba02bc767c6077a87c7ea66968","abstract_canon_sha256":"7b43d7a47ff6e359836e492d93c7af4b5459915c4e3e3e6a1547a429ebdfbe9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:05.341062Z","signature_b64":"RAkEdhQER4jFeJVl+r77N5UWwdQ4q48J/+wUcCrkyyP9S8+g9Hpq2WZB8bqrdB/Vho/dged2xO3XxTFlyA8NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"066b0f5d3373668663902e620f2d0d6b24cdf3a41c540a078578618a38831ddc","last_reissued_at":"2026-07-05T07:30:05.340571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:05.340571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Better and Simpler Lower Bounds for Differentially Private Statistical Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DS","cs.IT","cs.LG","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Shyam Narayanan","submitted_at":"2023-10-10T04:02:43Z","abstract_excerpt":"We provide optimal lower bounds for two well-known parameter estimation (also known as statistical estimation) tasks in high dimensions with approximate differential privacy. First, we prove that for any $\\alpha \\le O(1)$, estimating the covariance of a Gaussian up to spectral error $\\alpha$ requires $\\tilde{\\Omega}\\left(\\frac{d^{3/2}}{\\alpha \\varepsilon} + \\frac{d}{\\alpha^2}\\right)$ samples, which is tight up to logarithmic factors. This result improves over previous work which established this for $\\alpha \\le O\\left(\\frac{1}{\\sqrt{d}}\\right)$, and is also simpler than previous work. Next, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06289","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/2310.06289/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":"2310.06289","created_at":"2026-07-05T07:30:05.340651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06289v2","created_at":"2026-07-05T07:30:05.340651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06289","created_at":"2026-07-05T07:30:05.340651+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZVQ6XJTONTI","created_at":"2026-07-05T07:30:05.340651+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZVQ6XJTONTIMY4Q","created_at":"2026-07-05T07:30:05.340651+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZVQ6XJT","created_at":"2026-07-05T07:30:05.340651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17895","citing_title":"Lower Bounds for Public-Private Learning under Distribution Shift","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM","json":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM.json","graph_json":"https://pith.science/api/pith-number/AZVQ6XJTONTIMY4QFZRA6LINNM/graph.json","events_json":"https://pith.science/api/pith-number/AZVQ6XJTONTIMY4QFZRA6LINNM/events.json","paper":"https://pith.science/paper/AZVQ6XJT"},"agent_actions":{"view_html":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM","download_json":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM.json","view_paper":"https://pith.science/paper/AZVQ6XJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06289&json=true","fetch_graph":"https://pith.science/api/pith-number/AZVQ6XJTONTIMY4QFZRA6LINNM/graph.json","fetch_events":"https://pith.science/api/pith-number/AZVQ6XJTONTIMY4QFZRA6LINNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM/action/storage_attestation","attest_author":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM/action/author_attestation","sign_citation":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM/action/citation_signature","submit_replication":"https://pith.science/pith/AZVQ6XJTONTIMY4QFZRA6LINNM/action/replication_record"}},"created_at":"2026-07-05T07:30:05.340651+00:00","updated_at":"2026-07-05T07:30:05.340651+00:00"}