{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:72FIQ27W2GYLG3MAIX5EO4CQOD","short_pith_number":"pith:72FIQ27W","schema_version":"1.0","canonical_sha256":"fe8a886bf6d1b0b36d8045fa47705070ebd326e420f7d783161f2c0756004299","source":{"kind":"arxiv","id":"1805.11643","version":3},"attestation_state":"computed","paper":{"title":"High Dimensional Robust Sparse Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Liu Liu, Tianyang Li, Yanyao Shen","submitted_at":"2018-05-29T18:33:23Z","abstract_excerpt":"We provide a novel -- and to the best of our knowledge, the first -- algorithm for high dimensional sparse regression with constant fraction of corruptions in explanatory and/or response variables. Our algorithm recovers the true sparse parameters with sub-linear sample complexity, in the presence of a constant fraction of arbitrary corruptions. Our main contribution is a robust variant of Iterative Hard Thresholding. Using this, we provide accurate estimators: when the covariance matrix in sparse regression is identity, our error guarantee is near information-theoretically optimal. We then de"},"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":"1805.11643","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T18:33:23Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"6b9c9b6aea7647e2321b5627ad504fa98f447445fbce411f7a3a6a849f61bbc7","abstract_canon_sha256":"224441446354ed936187114d688297c90398bc987835b8bd72429f3d2be63277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:43.250816Z","signature_b64":"7IsLjQF4DiN2Ibzp6MDbg6jwT9DPWZHkGodpBS/k+IXB9nJFRxCd8EunAvB3hlSuaos/b3Lcop0PbwWWoWhRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe8a886bf6d1b0b36d8045fa47705070ebd326e420f7d783161f2c0756004299","last_reissued_at":"2026-05-17T23:44:43.250274Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:43.250274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High Dimensional Robust Sparse Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Constantine Caramanis, Liu Liu, Tianyang Li, Yanyao Shen","submitted_at":"2018-05-29T18:33:23Z","abstract_excerpt":"We provide a novel -- and to the best of our knowledge, the first -- algorithm for high dimensional sparse regression with constant fraction of corruptions in explanatory and/or response variables. Our algorithm recovers the true sparse parameters with sub-linear sample complexity, in the presence of a constant fraction of arbitrary corruptions. Our main contribution is a robust variant of Iterative Hard Thresholding. Using this, we provide accurate estimators: when the covariance matrix in sparse regression is identity, our error guarantee is near information-theoretically optimal. We then de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11643","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":""},"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":"1805.11643","created_at":"2026-05-17T23:44:43.250369+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11643v3","created_at":"2026-05-17T23:44:43.250369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11643","created_at":"2026-05-17T23:44:43.250369+00:00"},{"alias_kind":"pith_short_12","alias_value":"72FIQ27W2GYL","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"72FIQ27W2GYLG3MA","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"72FIQ27W","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00927","citing_title":"A Unified Approach to Robust Mean Estimation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD","json":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD.json","graph_json":"https://pith.science/api/pith-number/72FIQ27W2GYLG3MAIX5EO4CQOD/graph.json","events_json":"https://pith.science/api/pith-number/72FIQ27W2GYLG3MAIX5EO4CQOD/events.json","paper":"https://pith.science/paper/72FIQ27W"},"agent_actions":{"view_html":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD","download_json":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD.json","view_paper":"https://pith.science/paper/72FIQ27W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11643&json=true","fetch_graph":"https://pith.science/api/pith-number/72FIQ27W2GYLG3MAIX5EO4CQOD/graph.json","fetch_events":"https://pith.science/api/pith-number/72FIQ27W2GYLG3MAIX5EO4CQOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD/action/storage_attestation","attest_author":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD/action/author_attestation","sign_citation":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD/action/citation_signature","submit_replication":"https://pith.science/pith/72FIQ27W2GYLG3MAIX5EO4CQOD/action/replication_record"}},"created_at":"2026-05-17T23:44:43.250369+00:00","updated_at":"2026-05-17T23:44:43.250369+00:00"}