Qing Zhou's Homepage
Professor of Statistics
Chair of Statistics & Data Science
Faculty, Graduate Program in Bioinformatics
University of California, Los Angeles
- UCLA Department of Statistics & Data Science
- 8125 Mathematical Sciences Building, Box 951554
- Los Angeles, CA 90095
- Email: zhou@stat.ucla.edu
- Phone: (310)794-7563
Research Interests:
- Causal machine learning: We develop statistical and machine learning methods and theory for causal discovery from large-scale, high-dimensional data. Encoding causality among a system of variables by a directed graphical model, causal discovery is achieved through structure learning of the underlying graph. Our recent work includes penalized likelihood methods, divide-and-conquer strategies, and constraint-based algorithms for structure learning of causal graphs under challenging settings involving latent confounding and complex data dependency. We also develop sequential decision-making algorithms under a causal context, integrating intervention design, causal discovery, and optimization in the face of uncertainty.
- Computational genomics: We develop computational methods for efficient analysis of large-scale, high-throughput genomic data, combining model-based and machine learning approaches for robust statistical inference. A central focus of our research is to infer gene regulatory networks by integrating diverse data sources, including RNA-seq, protein binding, chromatin interaction, and DNA sequence data. Our work has led to the construction of gene regulatory networks and identification of combinatorial regulatory signals in embryonic stem cells. In parallel, we have advanced novel statistical models and algorithms to infer alternative splicing patterns and uncover their underlying regulatory mechanisms.
- High-dimensional statistics: We are interested in uncertainty quantification for regularized sparse estimators with applications to statistical inference for high-dimensional models. We have developed the technique of estimator augmentation to characterize the sampling distribution of a lasso-type estimator, which allows us to integrate Markov chain Monte Carlo and importance sampling into statistical inference for high-dimensional models. Recently, we developed a projection and shrinkage method for constructing confidence sets in high-dimensional regression that combines inferential advantages of sparse regularization and Stein estimation.
- Monte Carlo methods: We develop Monte Carlo methods to estimate statistical and topological structures of a probability distribution, with applications in Bayesian inference and statistical physics. We are interested in exploring and reconstructing energy landscapes by estimating the density of states, the tree of sublevel sets, and the domain of attraction.
Sample Publications:
- Zhou, Q. (2025). Latent Structure and Causality: Inference from Data, World Scientific. [Book website] [Table of Contents]
- Zhou, K., Li, K.C., and Zhou, Q. (2023). Honest confidence sets for high-dimensional regression by projection and shrinkage. Journal of the American Statistical Association, 118: 469-488. [Reprint]
- Ye, Q., Amini, A.A., and Zhou, Q. (2021). Optimizing regularized Cholesky score for order-based learning of Bayesian networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43: 3555-3572. [Reprint]
- Aragam, B. and Zhou, Q. (2015). Concave penalized estimation of sparse Gaussian Bayesian networks. Journal of Machine Learning Research, 16: 2273-2328. [Reprint]
- Shen, S., Park, J.W., Lu, Z., Lin, L., Henry, M.D., Wu, Y.N., Zhou, Q., and Xing, Y. (2014). rMATS: Robust and flexible detection of differential alternative splicing from replicate RNA-Seq data. Proceedings of the National Academy of Sciences of USA, 111: E5593-E5601. [Reprint]
- Zhou, Q. (2014). Monte Carlo simulation for lasso-type problems by estimator augmentation. Journal of the American Statistical Association, 109: 1495-1516. [Reprint]
- Fu, F. and Zhou, Q. (2013). Learning sparse causal Gaussian networks with experimental intervention: Regularization and coordinate descent. Journal of the American Statistical Association, 108: 288-300. [Reprint]
- Zhou, Q. (2011). Random walk over basins of attraction to construct Ising energy landscapes. Physical Review Letters, 106: 180602. [Reprint]
- Sridharan, R., Tchieu, J., Mason, M.J., Yachechko, R., Kuoy, E., Horvath, S., Zhou, Q., and Plath, K. (2009). Role of the murine reprogramming factors in the induction of pluripotency. Cell, 136: 364-377. [Reprint]
- Kou, S.C.*, Zhou, Q.*, and Wong, W.H. (2006). Equi-energy sampler with applications in statistical inference and statistical mechanics (with discussion). Annals of Statistics, 34: 1581-1652. (*Equally contributed authors.) [Reprint]
- Zhou, Q. and Wong, W.H. (2004). CisModule: De novo discovery of cis-regulatory modules by hierarchical mixture modeling. Proceedings of the National Academy of Sciences of USA, 101: 12114-12119. [Reprint]
Short Bio:
-
Qing Zhou received his Bachelor's degree in Engineering (Automation) in 2000 and a Master's degree in Pattern Recognition and Intelligent Systems in 2001, both from Tsinghua University. He earned his Ph.D. in Statistics from Harvard University in 2006. After graduation, Dr. Zhou joined the Department of Statistics at UCLA, where he has served as assistant professor (2006-2012), associate professor (2012-2016) and professor (2016-present). He was the founding director (2015-2018) of the self-support Master of Applied Statistics program and has been the department chair since 2023. He is also a faculty member in the Bioinformatics interdepartmental program (2007-present). Dr. Zhou has published a book and many research papers in statistics, machine learning, and computational biology. His work has been recognized and supported by competitive research awards, including the NSF Career, NSF Big Data, and NIH R01 awards.