{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A7NESS6MLG5647HM2Q4HP5JBVK","short_pith_number":"pith:A7NESS6M","schema_version":"1.0","canonical_sha256":"07da494bcc59bbee7cecd43877f521aaae832cb9b49a94c744701ea976677538","source":{"kind":"arxiv","id":"1802.06485","version":2},"attestation_state":"computed","paper":{"title":"Robust Estimation via Robust Gradient Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Adarsh Prasad, Arun Sai Suggala, Pradeep Ravikumar, Sivaraman Balakrishnan","submitted_at":"2018-02-19T01:49:31Z","abstract_excerpt":"We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber epsilon-contamination model and in heavy-tailed settings. Our workhorse is a novel robust variant of gradient descent, and we provide conditions under which our gradient descent variant provides accurate estimators in a general convex risk minimization problem. We provide specific consequences of our theory for linear regression, logistic regression and for estimation of the canonical parameters in an exponential f"},"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":"1802.06485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-19T01:49:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"744ec25684568feac259633e1abf501ecd5fd22f3a4d523436ee4db814ada28e","abstract_canon_sha256":"c33f8c7104c88d26eab99685c0144b1dc29f96c192ebaecd056737499ce4491b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:59.584219Z","signature_b64":"uotmbKHNwCTEJ0UuN5Bk+erzhWFYdl0HVhjObkNXO2S0o/o9UZsqufCKF/rONSTC2zwoTnBTBzrz64+/7EX5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07da494bcc59bbee7cecd43877f521aaae832cb9b49a94c744701ea976677538","last_reissued_at":"2026-05-18T00:17:59.583577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:59.583577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Estimation via Robust Gradient Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Adarsh Prasad, Arun Sai Suggala, Pradeep Ravikumar, Sivaraman Balakrishnan","submitted_at":"2018-02-19T01:49:31Z","abstract_excerpt":"We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber epsilon-contamination model and in heavy-tailed settings. Our workhorse is a novel robust variant of gradient descent, and we provide conditions under which our gradient descent variant provides accurate estimators in a general convex risk minimization problem. We provide specific consequences of our theory for linear regression, logistic regression and for estimation of the canonical parameters in an exponential f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06485","kind":"arxiv","version":2},"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":"1802.06485","created_at":"2026-05-18T00:17:59.583679+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06485v2","created_at":"2026-05-18T00:17:59.583679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06485","created_at":"2026-05-18T00:17:59.583679+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7NESS6MLG56","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7NESS6MLG5647HM","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7NESS6M","created_at":"2026-05-18T12:32:13.499390+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":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK","json":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK.json","graph_json":"https://pith.science/api/pith-number/A7NESS6MLG5647HM2Q4HP5JBVK/graph.json","events_json":"https://pith.science/api/pith-number/A7NESS6MLG5647HM2Q4HP5JBVK/events.json","paper":"https://pith.science/paper/A7NESS6M"},"agent_actions":{"view_html":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK","download_json":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK.json","view_paper":"https://pith.science/paper/A7NESS6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06485&json=true","fetch_graph":"https://pith.science/api/pith-number/A7NESS6MLG5647HM2Q4HP5JBVK/graph.json","fetch_events":"https://pith.science/api/pith-number/A7NESS6MLG5647HM2Q4HP5JBVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK/action/storage_attestation","attest_author":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK/action/author_attestation","sign_citation":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK/action/citation_signature","submit_replication":"https://pith.science/pith/A7NESS6MLG5647HM2Q4HP5JBVK/action/replication_record"}},"created_at":"2026-05-18T00:17:59.583679+00:00","updated_at":"2026-05-18T00:17:59.583679+00:00"}