{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZPDAN65P5BHZ5QPNN3C35QEB4B","short_pith_number":"pith:ZPDAN65P","schema_version":"1.0","canonical_sha256":"cbc606fbafe84f9ec1ed6ec5bec081e04231165598446eefe7d862226a7bd94f","source":{"kind":"arxiv","id":"1808.03106","version":1},"attestation_state":"computed","paper":{"title":"Robust classification via MOM minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guillaume Lecu\\'e, Matthieu Lerasle, Timoth\\'ee Mathieu","submitted_at":"2018-08-09T12:00:41Z","abstract_excerpt":"We present an extension of Vapnik's classical empirical risk minimizer (ERM) where the empirical risk is replaced by a median-of-means (MOM) estimator, the new estimators are called MOM minimizers. While ERM is sensitive to corruption of the dataset for many classical loss functions used in classification, we show that MOM minimizers behave well in theory, in the sense that it achieves Vapnik's (slow) rates of convergence under weak assumptions: data are only required to have a finite second moment and some outliers may also have corrupted the dataset.\n  We propose an algorithm inspired by MOM"},"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":"1808.03106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-08-09T12:00:41Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"59763ff0caf48f577ddf5f7d692cec1d29c30b233ca986deead10b4bbeb3edc2","abstract_canon_sha256":"eb2649661d7e2a6c2ca0d7539ac15f92356be1b54f6f14bb755fd803ef29e82f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:30.184675Z","signature_b64":"66vOjUjBBhj+8BgRxBuDJFpaGGsKRIbZbyRnUIXPxIYfWJ2GV1bPevuTkRw015JkE9Tyg6uS1fDtl/Ofr+gwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc606fbafe84f9ec1ed6ec5bec081e04231165598446eefe7d862226a7bd94f","last_reissued_at":"2026-05-18T00:08:30.184051Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:30.184051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust classification via MOM minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Guillaume Lecu\\'e, Matthieu Lerasle, Timoth\\'ee Mathieu","submitted_at":"2018-08-09T12:00:41Z","abstract_excerpt":"We present an extension of Vapnik's classical empirical risk minimizer (ERM) where the empirical risk is replaced by a median-of-means (MOM) estimator, the new estimators are called MOM minimizers. While ERM is sensitive to corruption of the dataset for many classical loss functions used in classification, we show that MOM minimizers behave well in theory, in the sense that it achieves Vapnik's (slow) rates of convergence under weak assumptions: data are only required to have a finite second moment and some outliers may also have corrupted the dataset.\n  We propose an algorithm inspired by MOM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03106","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":""},"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":"1808.03106","created_at":"2026-05-18T00:08:30.184151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03106v1","created_at":"2026-05-18T00:08:30.184151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03106","created_at":"2026-05-18T00:08:30.184151+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPDAN65P5BHZ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPDAN65P5BHZ5QPN","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPDAN65P","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02707","citing_title":"Algorithms of Robust Stochastic Optimization Based on Mirror Descent Method","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B","json":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B.json","graph_json":"https://pith.science/api/pith-number/ZPDAN65P5BHZ5QPNN3C35QEB4B/graph.json","events_json":"https://pith.science/api/pith-number/ZPDAN65P5BHZ5QPNN3C35QEB4B/events.json","paper":"https://pith.science/paper/ZPDAN65P"},"agent_actions":{"view_html":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B","download_json":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B.json","view_paper":"https://pith.science/paper/ZPDAN65P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03106&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPDAN65P5BHZ5QPNN3C35QEB4B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPDAN65P5BHZ5QPNN3C35QEB4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B/action/storage_attestation","attest_author":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B/action/author_attestation","sign_citation":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B/action/citation_signature","submit_replication":"https://pith.science/pith/ZPDAN65P5BHZ5QPNN3C35QEB4B/action/replication_record"}},"created_at":"2026-05-18T00:08:30.184151+00:00","updated_at":"2026-05-18T00:08:30.184151+00:00"}