Pan Xu

Assistant Professor of Biostatistics & Bioinformatics

My research is centered around Machine Learning, with broad interests in the areas of Artificial Intelligence, Data Science, Optimization, Reinforcement Learning, High Dimensional Statistics, and their applications to real-world problems including Bioinformatics and Healthcare. My research goal is to develop computationally- and data-efficient machine learning algorithms with both strong empirical performance and theoretical guarantees.

Appointments and Affiliations

  • Assistant Professor of Biostatistics & Bioinformatics
  • Assistant Professor in the Department of Electrical and Computer Engineering
  • Assistant Professor of Computer Science

Contact Information

Education

  • Ph.D. University of California - Los Angeles, 2021

Research Interests

Artificial Intelligence, Data Science, Optimization, Reinforcement Learning, and High Dimensional Statistics

Courses Taught

  • BIOSTAT 825: Foundation of Reinforcement Learning
  • COMPSCI 391: Independent Study

Representative Publications

  • Shea, Katriona, Rebecca K. Borchering, William J. M. Probert, Emily Howerton, Tiffany L. Bogich, Shou-Li Li, Willem G. van Panhuis, et al. “Multiple models for outbreak decision support in the face of uncertainty.” Proc Natl Acad Sci U S A 120, no. 18 (May 2, 2023): e2207537120. https://doi.org/10.1073/pnas.2207537120.
  • Zhang, Y., G. Qu, P. Xu, Y. Lin, Z. Chen, and A. Wierman. “Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning.” Proceedings of the Acm on Measurement and Analysis of Computing Systems 7, no. 1 (February 28, 2023). https://doi.org/10.1145/3579443.
  • Xu, Pan, Hongkai Zheng, Eric Mazumdar, Kamyar Azizzadenesheli, and Anima Anandkumar. “Langevin Monte Carlo for Contextual Bandits.” PMLR, 2022.
  • Cramer, Estee Y., Evan L. Ray, Velma K. Lopez, Johannes Bracher, Andrea Brennen, Alvaro J. Castro Rivadeneira, Aaron Gerding, et al. “Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the United States.” Proc Natl Acad Sci U S A 119, no. 15 (April 12, 2022): e2113561119. https://doi.org/10.1073/pnas.2113561119.
  • Zou, D., P. Xu, and Q. Gu. “Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling.” In 37th Conference on Uncertainty in Artificial Intelligence, Uai 2021, 1152–62, 2021.