{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JUUV4AHXEO7FY52IEAPZDIQU62","short_pith_number":"pith:JUUV4AHX","schema_version":"1.0","canonical_sha256":"4d295e00f723be5c7748201f91a214f6868a56f18c3036119fe695a0aa1ce02f","source":{"kind":"arxiv","id":"2005.01378","version":1},"attestation_state":"computed","paper":{"title":"High-Dimensional Robust Mean Estimation via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Ilias Diakonikolas, Mahdi Soltanolkotabi, Rong Ge, Yu Cheng","submitted_at":"2020-05-04T10:48:04Z","abstract_excerpt":"We study the problem of high-dimensional robust mean estimation in the presence of a constant fraction of adversarial outliers. A recent line of work has provided sophisticated polynomial-time algorithms for this problem with dimension-independent error guarantees for a range of natural distribution families.\n  In this work, we show that a natural non-convex formulation of the problem can be solved directly by gradient descent. Our approach leverages a novel structural lemma, roughly showing that any approximate stationary point of our non-convex objective gives a near-optimal solution to the "},"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":"2005.01378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T10:48:04Z","cross_cats_sorted":["cs.DS","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"6ef55578fe8382bcb3e15c7b3499abfc956c0c19b60c154c05703648d62b55fb","abstract_canon_sha256":"07e7d88f213bd2d7e35e76cc0160c13685e2f18799c517c0bd060b9a163e621f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:07.163886Z","signature_b64":"IY3I39xnP7wLtiynwcsEINuD1aZ2f+oN57Mx83q4xaQVi7rdUqcEI6mwG2MVsK9ty/LYnybpiYTrwssXiLtgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d295e00f723be5c7748201f91a214f6868a56f18c3036119fe695a0aa1ce02f","last_reissued_at":"2026-07-05T01:00:07.163467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:07.163467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Dimensional Robust Mean Estimation via Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Ilias Diakonikolas, Mahdi Soltanolkotabi, Rong Ge, Yu Cheng","submitted_at":"2020-05-04T10:48:04Z","abstract_excerpt":"We study the problem of high-dimensional robust mean estimation in the presence of a constant fraction of adversarial outliers. A recent line of work has provided sophisticated polynomial-time algorithms for this problem with dimension-independent error guarantees for a range of natural distribution families.\n  In this work, we show that a natural non-convex formulation of the problem can be solved directly by gradient descent. Our approach leverages a novel structural lemma, roughly showing that any approximate stationary point of our non-convex objective gives a near-optimal solution to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01378","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/2005.01378/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":"2005.01378","created_at":"2026-07-05T01:00:07.163535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.01378v1","created_at":"2026-07-05T01:00:07.163535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01378","created_at":"2026-07-05T01:00:07.163535+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUUV4AHXEO7F","created_at":"2026-07-05T01:00:07.163535+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUUV4AHXEO7FY52I","created_at":"2026-07-05T01:00:07.163535+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUUV4AHX","created_at":"2026-07-05T01:00:07.163535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62","json":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62.json","graph_json":"https://pith.science/api/pith-number/JUUV4AHXEO7FY52IEAPZDIQU62/graph.json","events_json":"https://pith.science/api/pith-number/JUUV4AHXEO7FY52IEAPZDIQU62/events.json","paper":"https://pith.science/paper/JUUV4AHX"},"agent_actions":{"view_html":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62","download_json":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62.json","view_paper":"https://pith.science/paper/JUUV4AHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.01378&json=true","fetch_graph":"https://pith.science/api/pith-number/JUUV4AHXEO7FY52IEAPZDIQU62/graph.json","fetch_events":"https://pith.science/api/pith-number/JUUV4AHXEO7FY52IEAPZDIQU62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62/action/storage_attestation","attest_author":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62/action/author_attestation","sign_citation":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62/action/citation_signature","submit_replication":"https://pith.science/pith/JUUV4AHXEO7FY52IEAPZDIQU62/action/replication_record"}},"created_at":"2026-07-05T01:00:07.163535+00:00","updated_at":"2026-07-05T01:00:07.163535+00:00"}