Overview

The main interests in my group are the theoretical foundations of modern machine learning, including deep learning, and the efficient statistical analysis of “big data” using advanced tools, such as those from random matrix theory. We aim to develop statistical and machine learning methods for efficient analysis of large datasets. We are part of several collaborative efforts, including the NSF-Simons Collaboration on the Mathematical and Scientific Foundations of Deep Learning, NSF TRIPODS, and ARO MURI on Robust Concept Learning.