Eliza O’Reillyمشاهده پروفایل
استادیار
Eliza O’Reilly is an Assistant Professor in the Department of Applied Mathematics & Statistics at Johns Hopkins University (JHU) and a member of the Data Science and AI Institute. Her research focuses on the mathematical foundations of data science, combining stochastic and convex geometry, high-dimensional probability, and statistical learning theory. She develops geometric models and algorithms for analyzing complex data structures, with applications in machine learning, optimization, and high-dimensional statistics. Dr. O’Reilly holds a B.S. in Mathematics from the University of Pittsburgh (2013) and a Ph.D. in Mathematics from the University of Texas at Austin (2019), where she was advised by François Baccelli. She completed a postdoctoral fellowship at the California Institute of Technology (2019–2022), sponsored by Venkat Chandrasekaran and Joel Tropp. Her work has been supported by NSF fellowships, including a NSF Graduate Research Fellowship and a NSF Postdoctoral Research Fellowship. Her research interests include: Randomized partitioning algorithms (e.g., Mondrian forests) Regularization in statistical inference and inverse problems Convex and nonconvex optimization methods Determinantal point processes and repulsive models High-dimensional geometry of random convex sets Her publications span theoretical guarantees for machine learning algorithms, optimization frameworks for data-driven problems, and geometric analysis of stochastic processes. Notable contributions include minimax analyses for random tessellation forests and spectral methods for convex regression. She actively collaborates with researchers in applied mathematics, statistics, and computer science.









