{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RZIM3A5P5S3TSHKNBFWQHSLW6J","short_pith_number":"pith:RZIM3A5P","schema_version":"1.0","canonical_sha256":"8e50cd83afecb7391d4d096d03c976f2457fecbcdf34a3d4edc7c38f1814720f","source":{"kind":"arxiv","id":"2106.13329","version":3},"attestation_state":"computed","paper":{"title":"Covariance-Aware Private Mean Estimation Without Private Covariance Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Smith, Gavin Brown, Jonathan Ullman, Lydia Zakynthinou, Marco Gaboardi","submitted_at":"2021-06-24T21:40:07Z","abstract_excerpt":"We present two sample-efficient differentially private mean estimators for $d$-dimensional (sub)Gaussian distributions with unknown covariance. Informally, given $n \\gtrsim d/\\alpha^2$ samples from such a distribution with mean $\\mu$ and covariance $\\Sigma$, our estimators output $\\tilde\\mu$ such that $\\| \\tilde\\mu - \\mu \\|_{\\Sigma} \\leq \\alpha$, where $\\| \\cdot \\|_{\\Sigma}$ is the Mahalanobis distance. All previous estimators with the same guarantee either require strong a priori bounds on the covariance matrix or require $\\Omega(d^{3/2})$ samples.\n  Each of our estimators is based on a simpl"},"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":"2106.13329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T21:40:07Z","cross_cats_sorted":[],"title_canon_sha256":"59aef315cd89cf96f78ddc62edbbebfd405a6c8e65830dbf632840b40e9e1ebd","abstract_canon_sha256":"4ed9d0a0238a156ffb7e962eee33d26363b2f61f64fbf8388991f01336548330"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:29.464517Z","signature_b64":"SowoPW8zAJO+J7g8eCwP/Jw2cNXbN2UBYRLSpBy9xztit7OPxgHEFsDhVOI/dFgMREG8dsZL9JwVUtxnbvL3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e50cd83afecb7391d4d096d03c976f2457fecbcdf34a3d4edc7c38f1814720f","last_reissued_at":"2026-07-05T08:00:29.463997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:29.463997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Covariance-Aware Private Mean Estimation Without Private Covariance Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Smith, Gavin Brown, Jonathan Ullman, Lydia Zakynthinou, Marco Gaboardi","submitted_at":"2021-06-24T21:40:07Z","abstract_excerpt":"We present two sample-efficient differentially private mean estimators for $d$-dimensional (sub)Gaussian distributions with unknown covariance. Informally, given $n \\gtrsim d/\\alpha^2$ samples from such a distribution with mean $\\mu$ and covariance $\\Sigma$, our estimators output $\\tilde\\mu$ such that $\\| \\tilde\\mu - \\mu \\|_{\\Sigma} \\leq \\alpha$, where $\\| \\cdot \\|_{\\Sigma}$ is the Mahalanobis distance. All previous estimators with the same guarantee either require strong a priori bounds on the covariance matrix or require $\\Omega(d^{3/2})$ samples.\n  Each of our estimators is based on a simpl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13329","kind":"arxiv","version":3},"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/2106.13329/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":"2106.13329","created_at":"2026-07-05T08:00:29.464074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13329v3","created_at":"2026-07-05T08:00:29.464074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13329","created_at":"2026-07-05T08:00:29.464074+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZIM3A5P5S3T","created_at":"2026-07-05T08:00:29.464074+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZIM3A5P5S3TSHKN","created_at":"2026-07-05T08:00:29.464074+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZIM3A5P","created_at":"2026-07-05T08:00:29.464074+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/RZIM3A5P5S3TSHKNBFWQHSLW6J","json":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J.json","graph_json":"https://pith.science/api/pith-number/RZIM3A5P5S3TSHKNBFWQHSLW6J/graph.json","events_json":"https://pith.science/api/pith-number/RZIM3A5P5S3TSHKNBFWQHSLW6J/events.json","paper":"https://pith.science/paper/RZIM3A5P"},"agent_actions":{"view_html":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J","download_json":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J.json","view_paper":"https://pith.science/paper/RZIM3A5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13329&json=true","fetch_graph":"https://pith.science/api/pith-number/RZIM3A5P5S3TSHKNBFWQHSLW6J/graph.json","fetch_events":"https://pith.science/api/pith-number/RZIM3A5P5S3TSHKNBFWQHSLW6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J/action/storage_attestation","attest_author":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J/action/author_attestation","sign_citation":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J/action/citation_signature","submit_replication":"https://pith.science/pith/RZIM3A5P5S3TSHKNBFWQHSLW6J/action/replication_record"}},"created_at":"2026-07-05T08:00:29.464074+00:00","updated_at":"2026-07-05T08:00:29.464074+00:00"}