{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2LJ2IPR4OGYHKSHJVT4P5H2JP3","short_pith_number":"pith:2LJ2IPR4","schema_version":"1.0","canonical_sha256":"d2d3a43e3c71b07548e9acf8fe9f497ef5fb224c1d1e7bbf385bfbc6c6625711","source":{"kind":"arxiv","id":"2102.05858","version":3},"attestation_state":"computed","paper":{"title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Chung-Wei Lee, Haipeng Luo, Mengxiao Zhang, Xiaojin Zhang","submitted_at":"2021-02-11T06:21:30Z","abstract_excerpt":"In this work, we develop linear bandit algorithms that automatically adapt to different environments. By plugging a novel loss estimator into the optimization problem that characterizes the instance-optimal strategy, our first algorithm not only achieves nearly instance-optimal regret in stochastic environments, but also works in corrupted environments with additional regret being the amount of corruption, while the state-of-the-art (Li et al., 2019) achieves neither instance-optimality nor the optimal dependence on the corruption amount. Moreover, by equipping this algorithm with an adversari"},"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":"2102.05858","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-11T06:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"e4442fe345b605eaafc032d7575f46579e2f3806d40fe532a80f55c137f4f02f","abstract_canon_sha256":"e6b6d7f12e543a4d7377cb6345bef9f0ec9bf66c65ddfa912df2ae5061e995e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:59.584087Z","signature_b64":"+dQhG9R25dvw+HGDfS72nGliiK++xQp6HC3XChVyAn+GcKUYKRUSzVxTYIJKAApSoWCZMut/Y04u+TuZ643gCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d3a43e3c71b07548e9acf8fe9f497ef5fb224c1d1e7bbf385bfbc6c6625711","last_reissued_at":"2026-07-05T02:48:59.583624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:59.583624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chen-Yu Wei, Chung-Wei Lee, Haipeng Luo, Mengxiao Zhang, Xiaojin Zhang","submitted_at":"2021-02-11T06:21:30Z","abstract_excerpt":"In this work, we develop linear bandit algorithms that automatically adapt to different environments. By plugging a novel loss estimator into the optimization problem that characterizes the instance-optimal strategy, our first algorithm not only achieves nearly instance-optimal regret in stochastic environments, but also works in corrupted environments with additional regret being the amount of corruption, while the state-of-the-art (Li et al., 2019) achieves neither instance-optimality nor the optimal dependence on the corruption amount. Moreover, by equipping this algorithm with an adversari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05858","kind":"arxiv","version":3},"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/2102.05858/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":"2102.05858","created_at":"2026-07-05T02:48:59.583682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05858v3","created_at":"2026-07-05T02:48:59.583682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05858","created_at":"2026-07-05T02:48:59.583682+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LJ2IPR4OGYH","created_at":"2026-07-05T02:48:59.583682+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LJ2IPR4OGYHKSHJ","created_at":"2026-07-05T02:48:59.583682+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LJ2IPR4","created_at":"2026-07-05T02:48:59.583682+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/2LJ2IPR4OGYHKSHJVT4P5H2JP3","json":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3.json","graph_json":"https://pith.science/api/pith-number/2LJ2IPR4OGYHKSHJVT4P5H2JP3/graph.json","events_json":"https://pith.science/api/pith-number/2LJ2IPR4OGYHKSHJVT4P5H2JP3/events.json","paper":"https://pith.science/paper/2LJ2IPR4"},"agent_actions":{"view_html":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3","download_json":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3.json","view_paper":"https://pith.science/paper/2LJ2IPR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05858&json=true","fetch_graph":"https://pith.science/api/pith-number/2LJ2IPR4OGYHKSHJVT4P5H2JP3/graph.json","fetch_events":"https://pith.science/api/pith-number/2LJ2IPR4OGYHKSHJVT4P5H2JP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3/action/storage_attestation","attest_author":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3/action/author_attestation","sign_citation":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3/action/citation_signature","submit_replication":"https://pith.science/pith/2LJ2IPR4OGYHKSHJVT4P5H2JP3/action/replication_record"}},"created_at":"2026-07-05T02:48:59.583682+00:00","updated_at":"2026-07-05T02:48:59.583682+00:00"}