{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PBOHSL6YR5KHVCQVXAKOBYJWUH","short_pith_number":"pith:PBOHSL6Y","schema_version":"1.0","canonical_sha256":"785c792fd88f547a8a15b814e0e136a1d702d9813ba1d659576810425a124e2a","source":{"kind":"arxiv","id":"2506.06861","version":1},"attestation_state":"computed","paper":{"title":"Differentially Private Sparse Linear Regression with Heavy-tailed Responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Di Wang, Meng Ding, Touming Tao, Xizhi Tian, Zihang Xiang","submitted_at":"2025-06-07T16:56:20Z","abstract_excerpt":"As a fundamental problem in machine learning and differential privacy (DP), DP linear regression has been extensively studied. However, most existing methods focus primarily on either regular data distributions or low-dimensional cases with irregular data. To address these limitations, this paper provides a comprehensive study of DP sparse linear regression with heavy-tailed responses in high-dimensional settings. In the first part, we introduce the DP-IHT-H method, which leverages the Huber loss and private iterative hard thresholding to achieve an estimation error bound of \\(\n  \\tilde{O}\\big"},"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":"2506.06861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T16:56:20Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"167965dd40a38682872d55f8727f178db3ad79a16bceabac114f23c4f525098e","abstract_canon_sha256":"b9cbcc853f90d48b78b3b27b4c691b668b116004071588c94305bba4852ea7ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:56.989183Z","signature_b64":"kbWQUPK+lVOnYGW9OCo2KHlRBKI+QAjfnrZHXWNuZnJORdnl5gp/+JJrKVG6CQXEryWNejK/1wj1nAVDi9+mBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"785c792fd88f547a8a15b814e0e136a1d702d9813ba1d659576810425a124e2a","last_reissued_at":"2026-07-05T11:17:56.988571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:56.988571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentially Private Sparse Linear Regression with Heavy-tailed Responses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Di Wang, Meng Ding, Touming Tao, Xizhi Tian, Zihang Xiang","submitted_at":"2025-06-07T16:56:20Z","abstract_excerpt":"As a fundamental problem in machine learning and differential privacy (DP), DP linear regression has been extensively studied. However, most existing methods focus primarily on either regular data distributions or low-dimensional cases with irregular data. To address these limitations, this paper provides a comprehensive study of DP sparse linear regression with heavy-tailed responses in high-dimensional settings. In the first part, we introduce the DP-IHT-H method, which leverages the Huber loss and private iterative hard thresholding to achieve an estimation error bound of \\(\n  \\tilde{O}\\big"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06861","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/2506.06861/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":"2506.06861","created_at":"2026-07-05T11:17:56.988649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06861v1","created_at":"2026-07-05T11:17:56.988649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06861","created_at":"2026-07-05T11:17:56.988649+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBOHSL6YR5KH","created_at":"2026-07-05T11:17:56.988649+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBOHSL6YR5KHVCQV","created_at":"2026-07-05T11:17:56.988649+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBOHSL6Y","created_at":"2026-07-05T11:17:56.988649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04668","citing_title":"Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH","json":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH.json","graph_json":"https://pith.science/api/pith-number/PBOHSL6YR5KHVCQVXAKOBYJWUH/graph.json","events_json":"https://pith.science/api/pith-number/PBOHSL6YR5KHVCQVXAKOBYJWUH/events.json","paper":"https://pith.science/paper/PBOHSL6Y"},"agent_actions":{"view_html":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH","download_json":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH.json","view_paper":"https://pith.science/paper/PBOHSL6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06861&json=true","fetch_graph":"https://pith.science/api/pith-number/PBOHSL6YR5KHVCQVXAKOBYJWUH/graph.json","fetch_events":"https://pith.science/api/pith-number/PBOHSL6YR5KHVCQVXAKOBYJWUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH/action/storage_attestation","attest_author":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH/action/author_attestation","sign_citation":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH/action/citation_signature","submit_replication":"https://pith.science/pith/PBOHSL6YR5KHVCQVXAKOBYJWUH/action/replication_record"}},"created_at":"2026-07-05T11:17:56.988649+00:00","updated_at":"2026-07-05T11:17:56.988649+00:00"}