{"total":17,"rows":[{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2111.03947","title":"Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2021-11-06","cited_by_count":43,"area":null},{"id":"2102.03758","title":"Non-stationary Online Learning with Memory and Non-stochastic Control","created":"2021-02-07","cited_by_count":33,"area":null},{"id":"2102.06933","title":"Revisiting Smoothed Online Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2102.13028","title":"Batched Neural Bandits","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2106.01420","title":"Parallelizing Thompson Sampling","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2210.13537","title":"Private Online Prediction from Experts: Separations and Faster Rates","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2102.03803","title":"Lazy OCO: Online Convex Optimization on a Switching Budget","created":"2021-02-07","cited_by_count":14,"area":null},{"id":"2205.06846","title":"Optimal Comparator Adaptive Online Learning with Switching Cost","created":"2022-05-13","cited_by_count":9,"area":null},{"id":"2103.11370","title":"Online Convex Optimization with Continuous Switching Constraint","created":"2021-03-21","cited_by_count":6,"area":null},{"id":"2210.09903","title":"Online Convex Optimization with Unbounded Memory","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2209.09419","title":"Multi-armed Bandit Learning on a Graph","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2406.03620","title":"Private Online Learning via Lazy Algorithms","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2205.04860","title":"Universal Caching","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2601.15984","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2409.19092","title":"Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2609.30556","title":"Dynamic Regret in Online Convex Optimization with Indicator Switching Costs","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}