The University of Arizona: Stochastic and Convex Geometry for Complex Data Analysis

Modern data science applications aim to efficiently and accurately extract important features and make predictions from high dimensional and large data sets.
Naturally occurring structure in the data underpins the success of many contemporary approaches, but large gaps between theory and practice remain. In this talk, I will present two different methods for nonparametric regression that can be viewed as a projection of a lifted formulation of the problem with a simple stochastic or convex geometric description, allowing the projection to encapsulate the data structure. In particular, I will first describe how the theory of stationary random tessellations in stochastic geometry addresses the computational and theoretical challenges of random decision forests with non-axis-aligned splits. Second, I will present a new approach to non-polyhedral convex regression that returns convex estimators compatible with semidefinite programming. These works open new questions at the intersection of stochastic and convex geometry, machine learning, and optimization.
Series: Special Colloquium
ENR2 S107
Presenter: Eliza O’Reilly, Cal Tech
  • Audience: Adult, STEM Professional
  • Genre: Mathematics
  • Type: Presentation

The event is finished.


Jan 18 2022


3:30 pm - 4:30 pm



More Info

More Information


The University of Arizona Environmental and Natural Resources 2 Building
1064 E. Lowell St., Tucson, AZ, 85719


The University of Arizona College of Mathematics
(520) 621-6866
QR Code