معرفی
Eliza O'Reilly is an Assistant Professor in the Department of Applied Mathematics & Statistics at Johns Hopkins University. Her research focuses on the intersections of stochastic geometry, convex geometry, high-dimensional probability, and statistical learning theory.
Her work explores:
- Nonconvex and convex regularizers in inverse problems
- Random tessellations and their machine learning applications
- Spectrahedral regression for convex function approximation
- Determinantal point processes for modeling repulsive interactions
- High-dimensional random convex sets and their asymptotic geometry
Her research is supported by the National Science Foundation. Recent publications investigate gradient-based dimension reduction, oblique decision trees, and geometric properties of regularizers. She has received her PhD from the University of Texas at Austin and was a postdoctoral scholar at Caltech.
۰مقاله ثبتشده
