{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4IOEEB2SJIU7CWSHYKFYW7KKCU","short_pith_number":"pith:4IOEEB2S","schema_version":"1.0","canonical_sha256":"e21c4207524a29f15a47c28b8b7d4a150c867db6114b2652205b04ef0706c472","source":{"kind":"arxiv","id":"2410.12677","version":2},"attestation_state":"computed","paper":{"title":"Efficient Optimization Algorithms for Linear Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Ant\\^onio H. Ribeiro, Dave Zahariah, Francis Bach, Thomas B. Sch\\\"on","submitted_at":"2024-10-16T15:41:08Z","abstract_excerpt":"Adversarial training can be used to learn models that are robust against perturbations. For linear models, it can be formulated as a convex optimization problem. Compared to methods proposed in the context of deep learning, leveraging the optimization structure allows significantly faster convergence rates. Still, the use of generic convex solvers can be inefficient for large-scale problems. Here, we propose tailored optimization algorithms for the adversarial training of linear models, which render large-scale regression and classification problems more tractable. For regression problems, we "},"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":"2410.12677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-16T15:41:08Z","cross_cats_sorted":["cs.CR","cs.LG","math.OC"],"title_canon_sha256":"b74655ad9b4c2c2ad27cf8d717f64c2c24e6c65a064b796864aba87978174491","abstract_canon_sha256":"24edf3e130b5d591271f685804b17317ef494ab8a36759a2e9b993e4c7ac7a6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:11.668726Z","signature_b64":"hAvAWWyRdPlkY8e1lvPqQ6VOP4+JfG8MdLCS3s25QhJXeywnHJBG+w3gEbqqXmMrMWiXtUqpbE4D1D0qfO2SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e21c4207524a29f15a47c28b8b7d4a150c867db6114b2652205b04ef0706c472","last_reissued_at":"2026-07-05T10:34:11.667656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:11.667656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Optimization Algorithms for Linear Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Ant\\^onio H. Ribeiro, Dave Zahariah, Francis Bach, Thomas B. Sch\\\"on","submitted_at":"2024-10-16T15:41:08Z","abstract_excerpt":"Adversarial training can be used to learn models that are robust against perturbations. For linear models, it can be formulated as a convex optimization problem. Compared to methods proposed in the context of deep learning, leveraging the optimization structure allows significantly faster convergence rates. Still, the use of generic convex solvers can be inefficient for large-scale problems. Here, we propose tailored optimization algorithms for the adversarial training of linear models, which render large-scale regression and classification problems more tractable. For regression problems, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12677","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/2410.12677/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":"2410.12677","created_at":"2026-07-05T10:34:11.667743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12677v2","created_at":"2026-07-05T10:34:11.667743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12677","created_at":"2026-07-05T10:34:11.667743+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IOEEB2SJIU7","created_at":"2026-07-05T10:34:11.667743+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IOEEB2SJIU7CWSH","created_at":"2026-07-05T10:34:11.667743+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IOEEB2S","created_at":"2026-07-05T10:34:11.667743+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/4IOEEB2SJIU7CWSHYKFYW7KKCU","json":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU.json","graph_json":"https://pith.science/api/pith-number/4IOEEB2SJIU7CWSHYKFYW7KKCU/graph.json","events_json":"https://pith.science/api/pith-number/4IOEEB2SJIU7CWSHYKFYW7KKCU/events.json","paper":"https://pith.science/paper/4IOEEB2S"},"agent_actions":{"view_html":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU","download_json":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU.json","view_paper":"https://pith.science/paper/4IOEEB2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12677&json=true","fetch_graph":"https://pith.science/api/pith-number/4IOEEB2SJIU7CWSHYKFYW7KKCU/graph.json","fetch_events":"https://pith.science/api/pith-number/4IOEEB2SJIU7CWSHYKFYW7KKCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU/action/storage_attestation","attest_author":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU/action/author_attestation","sign_citation":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU/action/citation_signature","submit_replication":"https://pith.science/pith/4IOEEB2SJIU7CWSHYKFYW7KKCU/action/replication_record"}},"created_at":"2026-07-05T10:34:11.667743+00:00","updated_at":"2026-07-05T10:34:11.667743+00:00"}