{"total":57,"rows":[{"id":"2112.13838","title":"Tracking Most Significant Arm Switches in Bandits","created":"2021-12-27","cited_by_count":27,"area":null},{"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":"2107.08861","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2212.03798","title":"Stochastic Rising Bandits","created":"2022-12-07","cited_by_count":18,"area":null},{"id":"2404.12366","title":"Accounting for AI and Users Shaping One Another: The Role of Mathematical Models","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2102.00725","title":"Generalized non-stationary bandits","created":"2021-02-01","cited_by_count":8,"area":null},{"id":"2110.11819","title":"A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2208.09254","title":"Mitigating Disparity while Maximizing Reward: Tight Anytime Guarantee for Improving Bandits","created":"2022-08-19","cited_by_count":8,"area":null},{"id":"2302.01377","title":"Learning with Exposure Constraints in Recommendation Systems","created":"2023-02-02","cited_by_count":8,"area":null},{"id":"2303.10373","title":"Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach","created":"2023-03-18","cited_by_count":8,"area":null},{"id":"2302.07510","title":"Best Arm Identification for Stochastic Rising Bandits","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2302.08345","title":"Linear Bandits with Memory: from Rotting to Rising","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2401.12722","title":"Falcon: Fair Active Learning using Multi-armed Bandits","created":"2024-01-23","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":"2205.14790","title":"Non-Stationary Bandits under Recharging Payoffs: Improved Planning with Sublinear Regret","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2302.06014","title":"Online Recommendations for Agents with Discounted Adaptive Preferences","created":"2023-02-12","cited_by_count":5,"area":null},{"id":"2201.12975","title":"Rotting Infinitely Many-armed Bandits","created":"2022-01-31","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":"2505.05226","title":"Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2204.11174","title":"Complete Policy Regret Bounds for Tallying Bandits","created":"2022-04-24","cited_by_count":3,"area":null},{"id":"2301.09251","title":"Congested Bandits: Optimal Routing via Short-term Resets","created":"2023-01-23","cited_by_count":3,"area":null},{"id":"2306.00338","title":"Last Switch Dependent Bandits with Monotone Payoff Functions","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2411.00707","title":"Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2305.02955","title":"Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality","created":"2023-05-04","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":"2404.14202","title":"An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2604.21432","title":"A single algorithm for both restless and rested rotting bandits","created":"2026-04-23","cited_by_count":2,"area":null},{"id":"2110.12118","title":"Bandits with Dynamic Arm-acquisition Costs","created":"2021-10-23","cited_by_count":1,"area":null},{"id":"2208.11926","title":"Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2212.06891","title":"Interactive Learning with Pricing for Optimal and Stable Allocations in Markets","created":"2022-12-13","cited_by_count":1,"area":null},{"id":"2303.02504","title":"MNL-Bandit in non-stationary environments","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2303.06552","title":"Energy Regularized RNNs for Solving Non-Stationary Bandit Problems","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2304.09088","title":"A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits","created":"2023-04-16","cited_by_count":1,"area":null},{"id":"2503.00650","title":"The Hidden Cost of Waiting for Accurate Predictions","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2509.20304","title":"Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2608.15848","title":"Generalized Linear Bandits with Memory","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2106.01624","title":"Sleeping Combinatorial Bandits","created":"2021-06-03","cited_by_count":0,"area":null},{"id":"2106.14813","title":"Offline Planning and Online Learning under Recovering Rewards","created":"2021-06-28","cited_by_count":0,"area":null},{"id":"2111.13026","title":"Bandit problems with fidelity rewards","created":"2021-11-25","cited_by_count":0,"area":null},{"id":"2201.05231","title":"Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version)","created":"2022-01-13","cited_by_count":0,"area":"diffusion"},{"id":"2206.09423","title":"Efficient End-to-End AutoML via Scalable Search Space Decomposition","created":"2022-06-19","cited_by_count":0,"area":null},{"id":"2403.00036","title":"Influencing Bandits: Arm Selection for Preference Shaping","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2403.11520","title":"State-Separated SARSA: A Practical Sequential Decision-Making Algorithm with Recovering Rewards","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2409.05980","title":"Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2410.05734","title":"Diminishing Exploration: A Minimalist Approach to Piecewise Stationary Multi-Armed Bandits","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2503.05662","title":"On Mitigating Affinity Bias through Bandits with Evolving Biased Feedback","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2504.08200","title":"Influential Bandits: Pulling an Arm May Change the Environment","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2602.10727","title":"Rising Multi-Armed Bandits with Known Horizons","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2605.08558","title":"Beyond Static Bias: Adaptive Multi-Fidelity Bandits with Improving Proxies","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.13546","title":"From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.06750","title":"Progressive Content Refinement with Decaying Reward Joint LinUCB","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.06772","title":"CAROL: Context-Aware Online Learning for Fuzzer Scheduling","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.37800","title":"Challenges and Solutions for Bandits in the Wild: Warm-Started Mixture Bandits for Cross-Cohort Slate Recommendation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00911","title":"Block Optimism for Nonstationary Bandits with Latent Linear Dynamics","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}