{"total":36,"rows":[{"id":"2403.07213","title":"Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits","created":"2024-03-11","cited_by_count":27,"area":null},{"id":"2212.03798","title":"Stochastic Rising Bandits","created":"2022-12-07","cited_by_count":18,"area":null},{"id":"2409.05181","title":"Sliding-Window Thompson Sampling for Non-Stationary Settings","created":"2024-09-08","cited_by_count":17,"area":null},{"id":"2102.00725","title":"Generalized non-stationary bandits","created":"2021-02-01","cited_by_count":8,"area":null},{"id":"2107.01835","title":"Fast Rate Learning in Stochastic First Price Bidding","created":"2021-07-05","cited_by_count":7,"area":null},{"id":"2203.13968","title":"Tuning Particle Accelerators with Safety Constraints using Bayesian Optimization","created":"2022-03-26","cited_by_count":7,"area":null},{"id":"2308.12000","title":"On Universally Optimal Algorithms for A/B Testing","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2402.15739","title":"Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery","created":"2024-02-24","cited_by_count":6,"area":null},{"id":"2411.01898","title":"Best-Arm Identification in Unimodal Bandits","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2106.01325","title":"Addressing the Long-term Impact of ML Decisions via Policy Regret","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2106.03790","title":"Multi-armed Bandit Requiring Monotone Arm Sequences","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2106.10166","title":"Problem Dependent View on Structured Thresholding Bandit Problems","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2312.12794","title":"Bandit Sequential Posted Pricing via Half-Concavity","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2405.11548","title":"Adaptive Online Experimental Design for Causal Discovery","created":"2024-05-19","cited_by_count":5,"area":null},{"id":"2112.01452","title":"Indexed Minimum Empirical Divergence for Unimodal Bandits","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2305.10718","title":"Discounted Thompson Sampling for Non-Stationary Bandit Problems","created":"2023-05-18","cited_by_count":4,"area":null},{"id":"2407.08654","title":"Adaptive Smooth Non-Stationary Bandits","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2503.07824","title":"Pure Exploration with Feedback Graphs","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2605.02462","title":"Black-box optimization of noisy functions with unknown smoothness","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2605.00489","title":"Revealing graph bandits for maximizing local influence","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2301.03456","title":"UB3: Best Beam Identification in Millimeter Wave Systems via Pure Exploration Unimodal Bandits","created":"2022-12-26","cited_by_count":1,"area":null},{"id":"2312.07285","title":"Forced Exploration in Bandit Problems","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2510.25811","title":"Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2106.08187","title":"Thompson Sampling for Unimodal Bandits","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2208.01511","title":"Unimodal Mono-Partite Matching in a Bandit Setting","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2208.01515","title":"UniRank: Unimodal Bandit Algorithm for Online Ranking","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2210.05222","title":"Stochastic Direct Search Method for Blind Resource Allocation","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2508.02909","title":"Clus-UCB: A Near-Optimal Algorithm for Clustered Bandits","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.02119","title":"Threshold-Based Optimal Arm Selection in Monotonic Bandits: Regret Lower Bounds and Algorithms","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2510.18299","title":"Physics-Informed Parametric Bandits for Beam Alignment in mmWave Communications","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.00605","title":"Efficient Matroid Bandit Linear Optimization Leveraging Unimodality","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2602.15972","title":"Fast Online Learning with Gaussian Prior-Driven Hierarchical Unimodal Thompson Sampling","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2604.25272","title":"Spectral bandits","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.03493","title":"Bandits on graphs and structures","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.01655","title":"MINTS: Minimalist Thompson Sampling","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.14690","title":"A Complexity Measure for Active Learning in Multi-group Mean Estimation","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":null}