{"total":33,"rows":[{"id":"2111.12482","title":"One More Step Towards Reality: Cooperative Bandits with Imperfect Communication","created":"2021-11-24","cited_by_count":15,"area":null},{"id":"2202.11795","title":"Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","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":"2109.01656","title":"Thompson Sampling for Bandits with Clustered Arms","created":"2021-09-06","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":"2108.01152","title":"Maximizing and Satisficing in Multi-armed Bandits with Graph Information","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2106.12200","title":"Random Effect Bandits","created":"2021-06-23","cited_by_count":4,"area":null},{"id":"2301.12755","title":"Efficient Node Selection in Private Personalized Decentralized Learning","created":"2023-01-30","cited_by_count":4,"area":null},{"id":"2501.14314","title":"Graph Feedback Bandits on Similar Arms: With and Without Graph Structures","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2212.06279","title":"Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2301.12822","title":"Evaluating COVID-19 vaccine allocation policies using Bayesian $m$-top exploration","created":"2023-01-30","cited_by_count":2,"area":null},{"id":"2307.11655","title":"Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2402.05144","title":"A Bandit Approach with Evolutionary Operators for Model Selection","created":"2024-02-07","cited_by_count":2,"area":null},{"id":"2404.15599","title":"Human-in-the-loop Learning for Dynamic Congestion Games","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2410.05785","title":"Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2606.07726","title":"Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2207.00109","title":"Ranking In Generalized Linear Bandits","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2211.03285","title":"SLOPT: Bandit Optimization Framework for Mutation-Based Fuzzing","created":"2022-11-07","cited_by_count":1,"area":null},{"id":"2312.15549","title":"Finite-Time Frequentist Regret Bounds of Multi-Agent Thompson Sampling on Sparse Hypergraphs","created":"2023-12-24","cited_by_count":1,"area":null},{"id":"2605.27073","title":"Learning to Orchestrate Agents under Uncertainty","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.03437","title":"Dynamically Allocating Evaluation Effort for Model Ranking","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2101.06592","title":"TSEC: a framework for online experimentation under experimental constraints","created":"2021-01-17","cited_by_count":0,"area":null},{"id":"2104.06339","title":"Deep imagination is a close to optimal policy for planning in large decision trees under limited resources","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2301.11802","title":"Decentralized Online Bandit Optimization on Directed Graphs with Regret Bounds","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2307.04695","title":"Cobalt: Optimizing Mining Rewards in Proof-of-Work Network Games","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2408.04310","title":"Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2505.19061","title":"Hierarchical Adversarial Bandits for Online Configuration Optimization","created":"2025-05-25","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":"2601.17430","title":"Active Hypothesis Testing for Correlated Combinatorial Anomaly Detection","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2603.16755","title":"A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.20628","title":"Human Decision-Making with AI Assistance under Correlated Features","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2610.03454","title":"Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}