{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5O3H7BCICNL2LYCKZ42BIG5ORZ","short_pith_number":"pith:5O3H7BCI","schema_version":"1.0","canonical_sha256":"ebb67f84481357a5e04acf34141bae8e4d2a1befd2e65c52dc53832f37ee9fab","source":{"kind":"arxiv","id":"1902.03794","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Structure of Uncertainty for Efficient Matroid Semi-Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michal Valko, Pierre Perrault, Vianney Perchet","submitted_at":"2019-02-11T09:59:05Z","abstract_excerpt":"We improve the efficiency of algorithms for stochastic \\emph{combinatorial semi-bandits}. In most interesting problems, state-of-the-art algorithms take advantage of structural properties of rewards, such as \\emph{independence}. However, while being optimal in terms of asymptotic regret, these algorithms are inefficient. In our paper, we first reduce their implementation to a specific \\emph{submodular maximization}. Then, in case of \\emph{matroid} constraints, we design adapted approximation routines, thereby providing the first efficient algorithms that rely on reward structure to improve reg"},"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":"1902.03794","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-11T09:59:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9bdee4c7737e7040023d373cfb7d899d47bf2b50d05b2d973a3ef7db43e15639","abstract_canon_sha256":"05d59c0d1a4dc5cc0ab6ceeb0866f337b199deb98728b7e86fb858a4468f61ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:48.472045Z","signature_b64":"snj4GVxcHnAoLLGlEMRWd+VYHVapUWg9kAhWnHN7SDtJBt0qre4XAPDyAndnrOgtMdVFNk3Q2lMRKrjgT5RQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebb67f84481357a5e04acf34141bae8e4d2a1befd2e65c52dc53832f37ee9fab","last_reissued_at":"2026-05-17T23:42:48.471533Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:48.471533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Structure of Uncertainty for Efficient Matroid Semi-Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michal Valko, Pierre Perrault, Vianney Perchet","submitted_at":"2019-02-11T09:59:05Z","abstract_excerpt":"We improve the efficiency of algorithms for stochastic \\emph{combinatorial semi-bandits}. In most interesting problems, state-of-the-art algorithms take advantage of structural properties of rewards, such as \\emph{independence}. However, while being optimal in terms of asymptotic regret, these algorithms are inefficient. In our paper, we first reduce their implementation to a specific \\emph{submodular maximization}. Then, in case of \\emph{matroid} constraints, we design adapted approximation routines, thereby providing the first efficient algorithms that rely on reward structure to improve reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03794","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":""},"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":"1902.03794","created_at":"2026-05-17T23:42:48.471608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.03794v2","created_at":"2026-05-17T23:42:48.471608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03794","created_at":"2026-05-17T23:42:48.471608+00:00"},{"alias_kind":"pith_short_12","alias_value":"5O3H7BCICNL2","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5O3H7BCICNL2LYCK","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5O3H7BCI","created_at":"2026-05-18T12:33:10.108867+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/5O3H7BCICNL2LYCKZ42BIG5ORZ","json":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ.json","graph_json":"https://pith.science/api/pith-number/5O3H7BCICNL2LYCKZ42BIG5ORZ/graph.json","events_json":"https://pith.science/api/pith-number/5O3H7BCICNL2LYCKZ42BIG5ORZ/events.json","paper":"https://pith.science/paper/5O3H7BCI"},"agent_actions":{"view_html":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ","download_json":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ.json","view_paper":"https://pith.science/paper/5O3H7BCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.03794&json=true","fetch_graph":"https://pith.science/api/pith-number/5O3H7BCICNL2LYCKZ42BIG5ORZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5O3H7BCICNL2LYCKZ42BIG5ORZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ/action/storage_attestation","attest_author":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ/action/author_attestation","sign_citation":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ/action/citation_signature","submit_replication":"https://pith.science/pith/5O3H7BCICNL2LYCKZ42BIG5ORZ/action/replication_record"}},"created_at":"2026-05-17T23:42:48.471608+00:00","updated_at":"2026-05-17T23:42:48.471608+00:00"}