{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3MAO75GE2W6SE5AHTOMZLKERKL","short_pith_number":"pith:3MAO75GE","schema_version":"1.0","canonical_sha256":"db00eff4c4d5bd2274079b9995a89152ff9b035cce78d67566e632a0539fed88","source":{"kind":"arxiv","id":"2301.13273","version":1},"attestation_state":"computed","paper":{"title":"Near Optimal Private and Robust Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Arun Sai Suggala, Prateek Jain, Sewoong Oh, Weihao Kong, Xiyang Liu","submitted_at":"2023-01-30T20:33:26Z","abstract_excerpt":"We study the canonical statistical estimation problem of linear regression from $n$ i.i.d.~examples under $(\\varepsilon,\\delta)$-differential privacy when some response variables are adversarially corrupted. We propose a variant of the popular differentially private stochastic gradient descent (DP-SGD) algorithm with two innovations: a full-batch gradient descent to improve sample complexity and a novel adaptive clipping to guarantee robustness. When there is no adversarial corruption, this algorithm improves upon the existing state-of-the-art approach and achieves a near optimal sample comple"},"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":"2301.13273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T20:33:26Z","cross_cats_sorted":["cs.CR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"d32e802be6179a6f258f06092ef5e7a2e153ded65d2a5def5695fdfe82956095","abstract_canon_sha256":"ec429b8def266f0599b1a187f44689fc08d1b0f2e6e42cfd8c6ffd34449d0265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:13.113535Z","signature_b64":"uaIPPYpSu0IO7OaEl8IF09HyMexAEh7Uc77yGOVCUvfz8uFMWpVTNJP2QjaYX54vBHDp18g0M1+an/kyaZfjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db00eff4c4d5bd2274079b9995a89152ff9b035cce78d67566e632a0539fed88","last_reissued_at":"2026-07-05T05:37:13.113049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:13.113049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near Optimal Private and Robust Linear Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Arun Sai Suggala, Prateek Jain, Sewoong Oh, Weihao Kong, Xiyang Liu","submitted_at":"2023-01-30T20:33:26Z","abstract_excerpt":"We study the canonical statistical estimation problem of linear regression from $n$ i.i.d.~examples under $(\\varepsilon,\\delta)$-differential privacy when some response variables are adversarially corrupted. We propose a variant of the popular differentially private stochastic gradient descent (DP-SGD) algorithm with two innovations: a full-batch gradient descent to improve sample complexity and a novel adaptive clipping to guarantee robustness. When there is no adversarial corruption, this algorithm improves upon the existing state-of-the-art approach and achieves a near optimal sample comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13273","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/2301.13273/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":"2301.13273","created_at":"2026-07-05T05:37:13.113115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13273v1","created_at":"2026-07-05T05:37:13.113115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13273","created_at":"2026-07-05T05:37:13.113115+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MAO75GE2W6S","created_at":"2026-07-05T05:37:13.113115+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MAO75GE2W6SE5AH","created_at":"2026-07-05T05:37:13.113115+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MAO75GE","created_at":"2026-07-05T05:37:13.113115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.01243","citing_title":"The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL","json":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL.json","graph_json":"https://pith.science/api/pith-number/3MAO75GE2W6SE5AHTOMZLKERKL/graph.json","events_json":"https://pith.science/api/pith-number/3MAO75GE2W6SE5AHTOMZLKERKL/events.json","paper":"https://pith.science/paper/3MAO75GE"},"agent_actions":{"view_html":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL","download_json":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL.json","view_paper":"https://pith.science/paper/3MAO75GE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13273&json=true","fetch_graph":"https://pith.science/api/pith-number/3MAO75GE2W6SE5AHTOMZLKERKL/graph.json","fetch_events":"https://pith.science/api/pith-number/3MAO75GE2W6SE5AHTOMZLKERKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL/action/storage_attestation","attest_author":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL/action/author_attestation","sign_citation":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL/action/citation_signature","submit_replication":"https://pith.science/pith/3MAO75GE2W6SE5AHTOMZLKERKL/action/replication_record"}},"created_at":"2026-07-05T05:37:13.113115+00:00","updated_at":"2026-07-05T05:37:13.113115+00:00"}