Ziping Xu
zipingxu at fas dot harvard dot edu
I am a Postdoctoral Fellow in Statistics at Harvard University with Professor Susan Murphy.
I obtained my PhD degree in Statistics from University of Michigan advised by Professor Ambuj Tewari. Before joining University of Michigan, I obtained my B.S. degree in Data Science from Peking University in 2018, where I was advised by Professor Song Xi Chen.
Research Interests. My primary research interests lie in the theory and practice in developing sequential decision-making approach for digital and mobile health. My works include designing sample-efficient online learning methods, statistical inference methods for adaptively collected data, and transfer/multitask learning approaches to address the continual nature of health applications.
I am on the 2024-2025 academic job market and would be happy to discuss any opportunities! Find my lastest CV here.
news
Aug 09, 2024 | I presented the poster “An Adaptation of RLSVI with Explicit Action Sampling Probabilities” at the first Reinforcement Learning Conference workshop Deployable RL: From Research to Practice tomorrow! This is a joint work with Iris Yan and Susan Murphy. For more information, see https://deployable-rl.github.io for more details. |
---|---|
Aug 05, 2024 | I gave the talk “The Fallacies of Minimizing Local Regret in the Sequential Task Setting” at JSM 2024! |
May 15, 2024 | My paper with Kevin Tan “A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage” was accepted by the first Reinforcement Learning Conference 2024. |
Mar 30, 2024 | Our paper “Online learning in bandits with predicted context” was accepted by AISTATS 2024 |
Jan 16, 2024 | Our paper “Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks” was accepted by ICLR 2024 |