{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:C5OS5Z5AEFFB6LXOL5FUHEJKSC","short_pith_number":"pith:C5OS5Z5A","schema_version":"1.0","canonical_sha256":"175d2ee7a0214a1f2eee5f4b43912a90a69905eea8c81170997aa3ae7777bedf","source":{"kind":"arxiv","id":"2007.15839","version":2},"attestation_state":"computed","paper":{"title":"Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Fred Zhang, Jerry Li, Samuel B. Hopkins","submitted_at":"2020-07-31T04:18:32Z","abstract_excerpt":"We study the problem of estimating the mean of a distribution in high dimensions when either the samples are adversarially corrupted or the distribution is heavy-tailed. Recent developments in robust statistics have established efficient and (near) optimal procedures for both settings. However, the algorithms developed on each side tend to be sophisticated and do not directly transfer to the other, with many of them having ad-hoc or complicated analyses.\n  In this paper, we provide a meta-problem and a duality theorem that lead to a new unified view on robust and heavy-tailed mean estimation i"},"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":"2007.15839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-07-31T04:18:32Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"9e16314bf5c635204d6d9577568986a616e14623fe7bf43a9d6a112f984ced52","abstract_canon_sha256":"d971d59182c1a6d3dfdf1d661f064d473b4a5b0e65b23bbe36126e7e9443264c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:48.633002Z","signature_b64":"/HW7hYMnfdIzQytMcK/zsacmqKUh3u6AyyDEzUJvoSRDleDEHfOKQA2+Q4pmCs6yM5fxR/17oiZhxFj92fFkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"175d2ee7a0214a1f2eee5f4b43912a90a69905eea8c81170997aa3ae7777bedf","last_reissued_at":"2026-07-05T02:07:48.632605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:48.632605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Fred Zhang, Jerry Li, Samuel B. Hopkins","submitted_at":"2020-07-31T04:18:32Z","abstract_excerpt":"We study the problem of estimating the mean of a distribution in high dimensions when either the samples are adversarially corrupted or the distribution is heavy-tailed. Recent developments in robust statistics have established efficient and (near) optimal procedures for both settings. However, the algorithms developed on each side tend to be sophisticated and do not directly transfer to the other, with many of them having ad-hoc or complicated analyses.\n  In this paper, we provide a meta-problem and a duality theorem that lead to a new unified view on robust and heavy-tailed mean estimation i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15839","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.15839/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":"2007.15839","created_at":"2026-07-05T02:07:48.632660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.15839v2","created_at":"2026-07-05T02:07:48.632660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15839","created_at":"2026-07-05T02:07:48.632660+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5OS5Z5AEFFB","created_at":"2026-07-05T02:07:48.632660+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5OS5Z5AEFFB6LXO","created_at":"2026-07-05T02:07:48.632660+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5OS5Z5A","created_at":"2026-07-05T02:07:48.632660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07694","citing_title":"Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of Gaussianity","ref_index":93,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC","json":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC.json","graph_json":"https://pith.science/api/pith-number/C5OS5Z5AEFFB6LXOL5FUHEJKSC/graph.json","events_json":"https://pith.science/api/pith-number/C5OS5Z5AEFFB6LXOL5FUHEJKSC/events.json","paper":"https://pith.science/paper/C5OS5Z5A"},"agent_actions":{"view_html":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC","download_json":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC.json","view_paper":"https://pith.science/paper/C5OS5Z5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.15839&json=true","fetch_graph":"https://pith.science/api/pith-number/C5OS5Z5AEFFB6LXOL5FUHEJKSC/graph.json","fetch_events":"https://pith.science/api/pith-number/C5OS5Z5AEFFB6LXOL5FUHEJKSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC/action/storage_attestation","attest_author":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC/action/author_attestation","sign_citation":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC/action/citation_signature","submit_replication":"https://pith.science/pith/C5OS5Z5AEFFB6LXOL5FUHEJKSC/action/replication_record"}},"created_at":"2026-07-05T02:07:48.632660+00:00","updated_at":"2026-07-05T02:07:48.632660+00:00"}