{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EMARQAO3VD4ZAMMNJSLRZ6PZEE","short_pith_number":"pith:EMARQAO3","schema_version":"1.0","canonical_sha256":"23011801dba8f990318d4c971cf9f9211b8511ba7338c9668e8b9559058668b1","source":{"kind":"arxiv","id":"2105.13939","version":2},"attestation_state":"computed","paper":{"title":"Efficient Online-Bandit Strategies for Minimax Learning Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christophe Roux, Elias Wirth, Sebastian Pokutta, Thomas Kerdreux","submitted_at":"2021-05-28T16:01:42Z","abstract_excerpt":"Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these problems are convex-linear problems where the minimization is carried out over the model parameters $w\\in\\mathcal{W}$ and the maximization over the empirical distribution $p\\in\\mathcal{K}$ of the training set indexes, where $\\mathcal{K}$ is the simplex or a subset of it. To design efficient methods, we let an online learning algorithm play against a (combinatorial) bandit algorithm. We argue that the efficiency of s"},"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":"2105.13939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T16:01:42Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"29e4d416bec8a699261abae5430ac2c741c24ac8a4f7ddd2fa98358326af6af4","abstract_canon_sha256":"c50588e9c7d6bce2ae785018c9e512b6b1f568349fe54ffaccd82bddaaaa75ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:14.223197Z","signature_b64":"Drg6ZPTs146WYgPUE2uIvm7Dn/pbg+3Dct0rLTXd5RdybyCeX0V8+9hqCYft1dJjbgqBxbDMkIDDmdI9pMZ3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23011801dba8f990318d4c971cf9f9211b8511ba7338c9668e8b9559058668b1","last_reissued_at":"2026-07-05T02:46:14.222784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:14.222784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Online-Bandit Strategies for Minimax Learning Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christophe Roux, Elias Wirth, Sebastian Pokutta, Thomas Kerdreux","submitted_at":"2021-05-28T16:01:42Z","abstract_excerpt":"Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these problems are convex-linear problems where the minimization is carried out over the model parameters $w\\in\\mathcal{W}$ and the maximization over the empirical distribution $p\\in\\mathcal{K}$ of the training set indexes, where $\\mathcal{K}$ is the simplex or a subset of it. To design efficient methods, we let an online learning algorithm play against a (combinatorial) bandit algorithm. We argue that the efficiency of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13939","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/2105.13939/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":"2105.13939","created_at":"2026-07-05T02:46:14.222839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.13939v2","created_at":"2026-07-05T02:46:14.222839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13939","created_at":"2026-07-05T02:46:14.222839+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMARQAO3VD4Z","created_at":"2026-07-05T02:46:14.222839+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMARQAO3VD4ZAMMN","created_at":"2026-07-05T02:46:14.222839+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMARQAO3","created_at":"2026-07-05T02:46:14.222839+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/EMARQAO3VD4ZAMMNJSLRZ6PZEE","json":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE.json","graph_json":"https://pith.science/api/pith-number/EMARQAO3VD4ZAMMNJSLRZ6PZEE/graph.json","events_json":"https://pith.science/api/pith-number/EMARQAO3VD4ZAMMNJSLRZ6PZEE/events.json","paper":"https://pith.science/paper/EMARQAO3"},"agent_actions":{"view_html":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE","download_json":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE.json","view_paper":"https://pith.science/paper/EMARQAO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.13939&json=true","fetch_graph":"https://pith.science/api/pith-number/EMARQAO3VD4ZAMMNJSLRZ6PZEE/graph.json","fetch_events":"https://pith.science/api/pith-number/EMARQAO3VD4ZAMMNJSLRZ6PZEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE/action/storage_attestation","attest_author":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE/action/author_attestation","sign_citation":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE/action/citation_signature","submit_replication":"https://pith.science/pith/EMARQAO3VD4ZAMMNJSLRZ6PZEE/action/replication_record"}},"created_at":"2026-07-05T02:46:14.222839+00:00","updated_at":"2026-07-05T02:46:14.222839+00:00"}