Xiongzhi Chen

Xiongzhi Chen is an Associate Professor in the Department of Mathematics and Statistics at Washington State University (WSU). He holds a PhD in Statistics from Purdue University (2012), and has postdoctoral experience at Princeton University (2013–2017). His research focuses on the mathematical and statistical foundations of non-Euclidean data analysis, deep learning, and high-dimensional inference. Key areas include Frechet mean estimation, geometric properties of neural networks, and simultaneous inference with applications in genomics and signal processing.

Education Background: PhD in Statistics (Purdue University, 2012), MA in Mathematics (University of Hawaii, 2009), MS in Mathematics (Sichuan University, 2006).

Research Interests: Chen’s work bridges mathematics, statistics, and computer science. He explores non-Euclidean data analysis (e.g., curvature estimation), deep learning foundations (geometric/topological properties of CNNs), and high-dimensional statistical methods. He emphasizes interdisciplinary collaboration and has secured funding from the Simons Foundation, NIH, and WSU.

Teaching: Chen teaches courses in statistical learning, data analytics, and probability, including Stat 577 (Statistical Learning Theory), Stat/Data 435/437, and Math 583 (Mathematics and Statistics of Deep Learning).

Grants & Funding: Supported by Simons Foundation, NIH, and WSU grants. His research team focuses on advancing theoretical and applied aspects of modern data science.

Labs/Teams: Leading an interdisciplinary research group at WSU, collaborating with experts in mathematics, statistics, and domain sciences. He emphasizes foundational theory combined with practical applications.