{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4J267LFFTVHKRTIFFPPBMPMGCW","short_pith_number":"pith:4J267LFF","schema_version":"1.0","canonical_sha256":"e275efaca59d4ea8cd052bde163d8615ab813bdc271d9d71c751a0fcd9f1416c","source":{"kind":"arxiv","id":"2411.06329","version":2},"attestation_state":"computed","paper":{"title":"Regret Minimization and Statistical Inference in Online Decision Making with High-dimensional Covariates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Congyuan Duan, Dong Xia, Jiashuo Jiang, Wanteng Ma","submitted_at":"2024-11-10T01:47:11Z","abstract_excerpt":"This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\\varepsilon$-greedy bandit algorithm for decision-making with a hard thresholding algorithm for estimating sparse bandit parameters and introduce an inference framework based on a debiasing method using inverse propensity weighting. Under a margin condition, our method achieves either $O(T^{1/2})$ regret or classical $O(T^{1/2})$-consistent inference, indicating an unavoidable trade-off between expl"},"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":"2411.06329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-10T01:47:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ab3204fd24a22052cf4041e3d13d37e7142e761d19984709f249aead5fc06c34","abstract_canon_sha256":"c9741982b5d05da6133d77aae34192eeb006c0b3fb9a387bd32679d443584307"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:41.699977Z","signature_b64":"wLh/mHNqTK84LYuH0Q2TGL6mwGV6U4CnrWLl1GVbte/Vo/9w6E+61Z7k4yTXUaaCZA1tE8gxWXCx9BE+s4OSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e275efaca59d4ea8cd052bde163d8615ab813bdc271d9d71c751a0fcd9f1416c","last_reissued_at":"2026-07-05T11:04:41.699483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:41.699483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret Minimization and Statistical Inference in Online Decision Making with High-dimensional Covariates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Congyuan Duan, Dong Xia, Jiashuo Jiang, Wanteng Ma","submitted_at":"2024-11-10T01:47:11Z","abstract_excerpt":"This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\\varepsilon$-greedy bandit algorithm for decision-making with a hard thresholding algorithm for estimating sparse bandit parameters and introduce an inference framework based on a debiasing method using inverse propensity weighting. Under a margin condition, our method achieves either $O(T^{1/2})$ regret or classical $O(T^{1/2})$-consistent inference, indicating an unavoidable trade-off between expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06329","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/2411.06329/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":"2411.06329","created_at":"2026-07-05T11:04:41.699541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06329v2","created_at":"2026-07-05T11:04:41.699541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06329","created_at":"2026-07-05T11:04:41.699541+00:00"},{"alias_kind":"pith_short_12","alias_value":"4J267LFFTVHK","created_at":"2026-07-05T11:04:41.699541+00:00"},{"alias_kind":"pith_short_16","alias_value":"4J267LFFTVHKRTIF","created_at":"2026-07-05T11:04:41.699541+00:00"},{"alias_kind":"pith_short_8","alias_value":"4J267LFF","created_at":"2026-07-05T11:04:41.699541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03736","citing_title":"Resource-Constrained Adaptive Inference for Sequential Pricing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15108","citing_title":"Logging Policy Design for Off-Policy Evaluation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15108","citing_title":"Logging Policy Design for Off-Policy Evaluation","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW","json":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW.json","graph_json":"https://pith.science/api/pith-number/4J267LFFTVHKRTIFFPPBMPMGCW/graph.json","events_json":"https://pith.science/api/pith-number/4J267LFFTVHKRTIFFPPBMPMGCW/events.json","paper":"https://pith.science/paper/4J267LFF"},"agent_actions":{"view_html":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW","download_json":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW.json","view_paper":"https://pith.science/paper/4J267LFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06329&json=true","fetch_graph":"https://pith.science/api/pith-number/4J267LFFTVHKRTIFFPPBMPMGCW/graph.json","fetch_events":"https://pith.science/api/pith-number/4J267LFFTVHKRTIFFPPBMPMGCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW/action/storage_attestation","attest_author":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW/action/author_attestation","sign_citation":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW/action/citation_signature","submit_replication":"https://pith.science/pith/4J267LFFTVHKRTIFFPPBMPMGCW/action/replication_record"}},"created_at":"2026-07-05T11:04:41.699541+00:00","updated_at":"2026-07-05T11:04:41.699541+00:00"}