{"total":55,"rows":[{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"area":null},{"id":"2110.09722","title":"Lipschitz Bandits with Batched Feedback","created":"2021-10-19","cited_by_count":21,"area":null},{"id":"2305.18543","title":"Robust Lipschitz Bandits to Adversarial Corruptions","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2402.16710","title":"Cost Aware Best Arm Identification","created":"2024-02-26","cited_by_count":13,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2312.12137","title":"Best Arm Identification with Fixed Budget: A Large Deviation Perspective","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2302.01539","title":"A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization","created":"2023-02-03","cited_by_count":9,"area":null},{"id":"2205.10936","title":"On Elimination Strategies for Bandit Fixed-Confidence Identification","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2206.02326","title":"Asymptotic Instance-Optimal Algorithms for Interactive Decision Making","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2106.10544","title":"Learning Space Partitions for Path Planning","created":"2021-06-19","cited_by_count":6,"area":null},{"id":"2202.06280","title":"On the complexity of All $\\varepsilon$-Best Arms Identification","created":"2022-02-13","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2211.15129","title":"On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2305.17402","title":"Learning and Collusion in Multi-unit Auctions","created":"2023-05-27","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":"2412.02988","title":"Preference-based Pure Exploration","created":"2024-12-04","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":"2401.07578","title":"Confounded Budgeted Causal Bandits","created":"2024-01-15","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":"2504.02251","title":"Quantum Lipschitz Bandits","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2110.14628","title":"(Almost) Free Incentivized Exploration from Decentralized Learning Agents","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2204.06910","title":"Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2210.12625","title":"Fast Beam Alignment via Pure Exploration in Multi-armed Bandits","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2312.04653","title":"Learning Thresholds with Latent Values and Censored Feedback","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2407.06321","title":"Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2503.08004","title":"Multiplayer Information Asymmetric Bandits in Metric Spaces","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2505.18871","title":"Non-Stationary Lipschitz Bandits","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2305.06082","title":"Best Arm Identification in Bandits with Limited Precision Sampling","created":"2023-05-10","cited_by_count":2,"area":null},{"id":"2405.05733","title":"Batched Stochastic Bandit for Nondegenerate Functions","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2410.09597","title":"A Complete Characterization of Learnability for Stochastic Noisy Bandits","created":"2024-10-12","cited_by_count":2,"area":null},{"id":"2502.04021","title":"Variational Quantum Optimization with Continuous Bandits","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2102.02472","title":"Transfer Learning in Bandits with Latent Continuity","created":"2021-02-04","cited_by_count":1,"area":null},{"id":"2106.14338","title":"Regret Analysis in Deterministic Reinforcement Learning","created":"2021-06-27","cited_by_count":1,"area":null},{"id":"2108.13810","title":"Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations","created":"2021-08-31","cited_by_count":1,"area":null},{"id":"2302.09440","title":"Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2409.01574","title":"Policy Gradients for Optimal Parallel Tempering MCMC","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2507.08994","title":"Fixed-Confidence Multiple Change Point Identification under Bandit Feedback","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2511.09766","title":"Ksurf-Drone: Attention Kalman Filter for Contextual Bandit Optimization in Cloud Resource Allocation","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2602.16965","title":"Multi-Agent Lipschitz Bandits","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.22128","title":"Computationally lightweight classifiers with frequentist bounds on predictions","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.13738","title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","cited_by_count":0,"area":null},{"id":"2305.11509","title":"From Random Search to Bandit Learning in Metric Measure Spaces","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2306.17329","title":"Kernel $\\epsilon$-Greedy for Multi-Armed Bandits with Covariates","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2410.18844","title":"Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2502.07397","title":"Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2502.13467","title":"On the Sublinear Regret of Continuous K-Max Bandits","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2503.07877","title":"Cost-Aware Optimal Pairwise Pure Exploration","created":"2025-03-10","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":"2604.19672","title":"Budgeted Online Influence Maximization","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.29748","title":"Instance-dependent Stochastic Lipschitz bandit","created":"2026-05-28","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},{"id":"2608.07922","title":"Memory--Batch Tradeoffs in Lipschitz Bandits","created":"2026-08-08","cited_by_count":0,"area":null}],"next_cursor":null}