{"total":33,"rows":[{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2209.02570","title":"When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits","created":"2022-09-06","cited_by_count":28,"area":null},{"id":"2202.05567","title":"Shuffle Private Linear Contextual Bandits","created":"2022-02-11","cited_by_count":27,"area":null},{"id":"2106.02575","title":"Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits","created":"2021-06-04","cited_by_count":25,"area":null},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23,"area":null},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","cited_by_count":22,"area":null},{"id":"2112.06008","title":"Privacy Amplification via Shuffling for Linear Contextual Bandits","created":"2021-12-11","cited_by_count":17,"area":null},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16,"area":null},{"id":"2102.03022","title":"Deceptive Reinforcement Learning for Privacy-Preserving Planning","created":"2021-02-05","cited_by_count":14,"area":null},{"id":"2206.05772","title":"Distributed Differential Privacy in Multi-Armed Bandits","created":"2022-06-12","cited_by_count":14,"area":null},{"id":"2110.10133","title":"Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2021-10-19","cited_by_count":13,"area":null},{"id":"2102.12467","title":"No-Regret Algorithms for Private Gaussian Process Bandit Optimization","created":"2021-02-24","cited_by_count":11,"area":null},{"id":"2112.01585","title":"Differentially Private Exploration in Reinforcement Learning with Linear Representation","created":"2021-12-02","cited_by_count":11,"area":null},{"id":"2202.01292","title":"Improved Regret for Differentially Private Exploration in Linear MDP","created":"2022-02-02","cited_by_count":8,"area":null},{"id":"2209.11837","title":"Doubly Fair Dynamic Pricing","created":"2022-09-23","cited_by_count":8,"area":null},{"id":"2108.11563","title":"Adaptive Control of Differentially Private Linear Quadratic Systems","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2201.10447","title":"Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization","created":"2022-01-25","cited_by_count":7,"area":null},{"id":"2301.00188","title":"New Challenges in Reinforcement Learning: A Survey of Security and Privacy","created":"2022-12-31","cited_by_count":7,"area":null},{"id":"2112.05495","title":"How Private Is Your RL Policy? An Inverse RL Based Analysis Framework","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2306.09273","title":"Privacy Risks in Reinforcement Learning for Household Robots","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2204.04858","title":"Stability and Generalization of Differentially Private Minimax Problems","created":"2022-04-11","cited_by_count":2,"area":null},{"id":"2301.12535","title":"Concurrent Shuffle Differential Privacy Under Continual Observation","created":"2023-01-29","cited_by_count":2,"area":null},{"id":"2109.08236","title":"Reinforcement Learning on Encrypted Data","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2203.10165","title":"Privacy-Preserving Reinforcement Learning Beyond Expectation","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2311.06255","title":"Privacy-Engineered Value Decomposition Networks for Cooperative Multi-Agent Reinforcement Learning","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2405.14038","title":"FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2407.09809","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2410.06878","title":"Noise is All You Need: Private Second-Order Convergence of Noisy SGD","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2605.01425","title":"Barriers to Counterfactual Credit Attribution for Autoregressive Models","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.01908","title":"Private and Stable Test-Time Adaptation with Differential Privacy","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}