Alert button
Picture for Yu-Xiang Wang

Yu-Xiang Wang

Alert button

Privacy Profiles for Private Selection

Feb 09, 2024
Antti Koskela, Rachel Redberg, Yu-Xiang Wang

Viaarxiv icon

Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs

Feb 08, 2024
Xuandong Zhao, Lei Li, Yu-Xiang Wang

Viaarxiv icon

Online Feature Updates Improve Online (Generalized) Label Shift Adaptation

Feb 05, 2024
Ruihan Wu, Siddhartha Datta, Yi Su, Dheeraj Baby, Yu-Xiang Wang, Kilian Q. Weinberger

Viaarxiv icon

Weak-to-Strong Jailbreaking on Large Language Models

Feb 05, 2024
Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang

Viaarxiv icon

Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints

Feb 02, 2024
Dan Qiao, Yu-Xiang Wang

Viaarxiv icon

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

Dec 31, 2023
Rachel Redberg, Antti Koskela, Yu-Xiang Wang

Viaarxiv icon

Pricing with Contextual Elasticity and Heteroscedastic Valuation

Dec 26, 2023
Jianyu Xu, Yu-Xiang Wang

Viaarxiv icon

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation

Nov 04, 2023
Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yi-An Ma

Figure 1 for Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Figure 2 for Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Figure 3 for Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Figure 4 for Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Viaarxiv icon

Communication-Efficient Federated Non-Linear Bandit Optimization

Nov 03, 2023
Chuanhao Li, Chong Liu, Yu-Xiang Wang

Figure 1 for Communication-Efficient Federated Non-Linear Bandit Optimization
Figure 2 for Communication-Efficient Federated Non-Linear Bandit Optimization
Figure 3 for Communication-Efficient Federated Non-Linear Bandit Optimization
Figure 4 for Communication-Efficient Federated Non-Linear Bandit Optimization
Viaarxiv icon