Wyman S437
Research Areas Math of data science Stochastic and convex geometry Point processes High dimensional probability Statistical learning theory

Eliza O’Reilly is an assistant professor in the Department of Applied Mathematics and Statistics. Her research focuses on the development and analysis of new geometric models and algorithms for complex data analysis that optimally adapt to underlying structure or constraints.

Her mathematical approach to these problems utilizes point process theory, stochastic geometry, convex geometry, and high dimensional probability. For example, her work employs the theory of stationary random tessellations to prove theoretical guarantees for randomized partitioning methods, such as random forests and random feature approximation. Her research also explores the capacity and limitations of convex approximation and regularization for signal recovery and prediction.

She received her bachelor’s degree in mathematics in 2013 from the University of Pittsburgh and her PhD in mathematics from the University of Texas at Austin in 2019. Since graduating, she has been a postdoctoral scholar at the California Institute of Technology. She has been awarded an NSF Graduate Research Fellowship, the UT Departmental Dissertation Excellence award, and an NSF Postdoctoral Research Fellowship.