{"total":25,"rows":[{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2303.02186","title":"Causal Deep Learning","created":"2023-03-03","cited_by_count":20,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2202.05100","title":"Adaptively Exploiting d-Separators with Causal Bandits","created":"2022-02-10","cited_by_count":18,"area":null},{"id":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17,"area":null},{"id":"2107.02772","title":"A Causal Bandit Approach to Learning Good Atomic Interventions in Presence of Unobserved Confounders","created":"2021-07-06","cited_by_count":15,"area":null},{"id":"2301.07040","title":"Optimal Algorithms for Latent Bandits with Cluster Structure","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2101.12506","title":"Learning User Preferences in Non-Stationary Environments","created":"2021-01-29","cited_by_count":10,"area":null},{"id":"2209.03997","title":"Online Low Rank Matrix Completion","created":"2022-09-08","cited_by_count":9,"area":null},{"id":"2305.04638","title":"Learning Good Interventions in Causal Graphs via Covering","created":"2023-05-08","cited_by_count":5,"area":null},{"id":"2201.12700","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2306.13053","title":"Context-lumpable stochastic bandits","created":"2023-06-22","cited_by_count":4,"area":null},{"id":"2307.13916","title":"Online learning in bandits with predicted context","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2311.16941","title":"Debiasing Multimodal Models via Causal Information Minimization","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2502.20153","title":"Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability","created":"2025-02-27","cited_by_count":4,"area":null},{"id":"2212.07524","title":"Invariant Lipschitz Bandits: A Side Observation Approach","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2405.18626","title":"Causal Contextual Bandits with Adaptive Context","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2408.14432","title":"Contextual Bandit with Herding Effects: Algorithms and Recommendation Applications","created":"2024-08-26","cited_by_count":1,"area":null},{"id":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2407.16239","title":"Identifiable Latent Bandits: Leveraging observational data for personalized decision-making","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2408.05843","title":"Online Matrix Completion: A Collaborative Approach with Hott Items","created":"2024-08-11","cited_by_count":0,"area":null},{"id":"2601.17430","title":"Active Hypothesis Testing for Correlated Combinatorial Anomaly Detection","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.00188","title":"Learning to Price: Interpretable Attribute-Level Models for Dynamic Markets","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.00193","title":"OTSS: Output-Targeted Soft Segmentation for Contextual Decision-Weight Learning","created":"2026-04-30","cited_by_count":0,"area":null}],"next_cursor":null}