{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C4ECWWTDX7IOH2M6XW6OQLI2JJ","short_pith_number":"pith:C4ECWWTD","schema_version":"1.0","canonical_sha256":"17082b5a63bfd0e3e99ebdbce82d1a4a5a4a16f483176445195e32b91c55e27a","source":{"kind":"arxiv","id":"2501.00265","version":1},"attestation_state":"computed","paper":{"title":"Outlier-Robust Training of Machine Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Charis Georgiou, Jingnan Shi, Luca Carlone, Rajat Talak","submitted_at":"2024-12-31T04:19:53Z","abstract_excerpt":"Robust training of machine learning models in the presence of outliers has garnered attention across various domains. The use of robust losses is a popular approach and is known to mitigate the impact of outliers. We bring to light two literatures that have diverged in their ways of designing robust losses: one using M-estimation, which is popular in robotics and computer vision, and another using a risk-minimization framework, which is popular in deep learning. We first show that a simple modification of the Black-Rangarajan duality provides a unifying view. The modified duality brings out a "},"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":"2501.00265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-31T04:19:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f95ce26022f03687db39aafa892decd91c07c3ef0c73e25b90418c69dc16c499","abstract_canon_sha256":"28b88ec86c54a832ed81d175b35ce851a68f960b4278292dfac6f4ed443ec68b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:41.937531Z","signature_b64":"oEooCwxuWq1am05Z2sO0DdbkW9FdxiM8tICZ+koye6iDhp+NtXjjMJZBN22rMTPPO4xcCErDGQH58etWBkNiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17082b5a63bfd0e3e99ebdbce82d1a4a5a4a16f483176445195e32b91c55e27a","last_reissued_at":"2026-07-05T09:55:41.937029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:41.937029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Outlier-Robust Training of Machine Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Charis Georgiou, Jingnan Shi, Luca Carlone, Rajat Talak","submitted_at":"2024-12-31T04:19:53Z","abstract_excerpt":"Robust training of machine learning models in the presence of outliers has garnered attention across various domains. The use of robust losses is a popular approach and is known to mitigate the impact of outliers. We bring to light two literatures that have diverged in their ways of designing robust losses: one using M-estimation, which is popular in robotics and computer vision, and another using a risk-minimization framework, which is popular in deep learning. We first show that a simple modification of the Black-Rangarajan duality provides a unifying view. The modified duality brings out a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00265","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/2501.00265/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":"2501.00265","created_at":"2026-07-05T09:55:41.937089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00265v1","created_at":"2026-07-05T09:55:41.937089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00265","created_at":"2026-07-05T09:55:41.937089+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4ECWWTDX7IO","created_at":"2026-07-05T09:55:41.937089+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4ECWWTDX7IOH2M6","created_at":"2026-07-05T09:55:41.937089+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4ECWWTD","created_at":"2026-07-05T09:55:41.937089+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/C4ECWWTDX7IOH2M6XW6OQLI2JJ","json":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ.json","graph_json":"https://pith.science/api/pith-number/C4ECWWTDX7IOH2M6XW6OQLI2JJ/graph.json","events_json":"https://pith.science/api/pith-number/C4ECWWTDX7IOH2M6XW6OQLI2JJ/events.json","paper":"https://pith.science/paper/C4ECWWTD"},"agent_actions":{"view_html":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ","download_json":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ.json","view_paper":"https://pith.science/paper/C4ECWWTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00265&json=true","fetch_graph":"https://pith.science/api/pith-number/C4ECWWTDX7IOH2M6XW6OQLI2JJ/graph.json","fetch_events":"https://pith.science/api/pith-number/C4ECWWTDX7IOH2M6XW6OQLI2JJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ/action/storage_attestation","attest_author":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ/action/author_attestation","sign_citation":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ/action/citation_signature","submit_replication":"https://pith.science/pith/C4ECWWTDX7IOH2M6XW6OQLI2JJ/action/replication_record"}},"created_at":"2026-07-05T09:55:41.937089+00:00","updated_at":"2026-07-05T09:55:41.937089+00:00"}