{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GPD5X5MJOQQLYGZGDFMRE4NX2T","short_pith_number":"pith:GPD5X5MJ","schema_version":"1.0","canonical_sha256":"33c7dbf5897420bc1b2619591271b7d4f17e707f11a82a8f407b6b24ee01301a","source":{"kind":"arxiv","id":"2503.24321","version":1},"attestation_state":"computed","paper":{"title":"Sample-Optimal Private Regression in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ML"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Mahbod Majid, Prashanti Anderson, Stefan Tiegel","submitted_at":"2025-03-31T17:08:12Z","abstract_excerpt":"We consider the task of privately obtaining prediction error guarantees in ordinary least-squares regression problems with Gaussian covariates (with unknown covariance structure). We provide the first sample-optimal polynomial time algorithm for this task under both pure and approximate differential privacy. We show that any improvement to the sample complexity of our algorithm would violate either statistical-query or information-theoretic lower bounds. Additionally, our algorithm is robust to a small fraction of arbitrary outliers and achieves optimal error rates as a function of the fractio"},"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":"2503.24321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2025-03-31T17:08:12Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ML"],"title_canon_sha256":"88e2dd3c9a33812ae70add421ccf42842a33fbf7cc89f6361b271ecab91ebace","abstract_canon_sha256":"b0731e5cf68a8046f3beb66a840f22189c1ba847ba6cd79d1dfcbcd009000ee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:08.325869Z","signature_b64":"ZXUSZ7dc6LhOiYQsguOOlaHoQwDve30HZLiMcsR/X5tiOTLKUI/U/6may9RKDkaHEmesNwbU6ehxim4mZ2D3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33c7dbf5897420bc1b2619591271b7d4f17e707f11a82a8f407b6b24ee01301a","last_reissued_at":"2026-07-05T10:42:08.325374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:08.325374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Optimal Private Regression in Polynomial Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ML"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Mahbod Majid, Prashanti Anderson, Stefan Tiegel","submitted_at":"2025-03-31T17:08:12Z","abstract_excerpt":"We consider the task of privately obtaining prediction error guarantees in ordinary least-squares regression problems with Gaussian covariates (with unknown covariance structure). We provide the first sample-optimal polynomial time algorithm for this task under both pure and approximate differential privacy. We show that any improvement to the sample complexity of our algorithm would violate either statistical-query or information-theoretic lower bounds. Additionally, our algorithm is robust to a small fraction of arbitrary outliers and achieves optimal error rates as a function of the fractio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24321","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/2503.24321/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":"2503.24321","created_at":"2026-07-05T10:42:08.325435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.24321v1","created_at":"2026-07-05T10:42:08.325435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24321","created_at":"2026-07-05T10:42:08.325435+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPD5X5MJOQQL","created_at":"2026-07-05T10:42:08.325435+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPD5X5MJOQQLYGZG","created_at":"2026-07-05T10:42:08.325435+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPD5X5MJ","created_at":"2026-07-05T10:42:08.325435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.21060","citing_title":"On the Sample Complexity of Differentially Private Policy Optimization","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T","json":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T.json","graph_json":"https://pith.science/api/pith-number/GPD5X5MJOQQLYGZGDFMRE4NX2T/graph.json","events_json":"https://pith.science/api/pith-number/GPD5X5MJOQQLYGZGDFMRE4NX2T/events.json","paper":"https://pith.science/paper/GPD5X5MJ"},"agent_actions":{"view_html":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T","download_json":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T.json","view_paper":"https://pith.science/paper/GPD5X5MJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.24321&json=true","fetch_graph":"https://pith.science/api/pith-number/GPD5X5MJOQQLYGZGDFMRE4NX2T/graph.json","fetch_events":"https://pith.science/api/pith-number/GPD5X5MJOQQLYGZGDFMRE4NX2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T/action/storage_attestation","attest_author":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T/action/author_attestation","sign_citation":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T/action/citation_signature","submit_replication":"https://pith.science/pith/GPD5X5MJOQQLYGZGDFMRE4NX2T/action/replication_record"}},"created_at":"2026-07-05T10:42:08.325435+00:00","updated_at":"2026-07-05T10:42:08.325435+00:00"}