My name is Cynthia Rush and I am the Howard Levene Assistant Professor of Statistics in the Department of Statistics at Columbia University. In May, 2016, I received my Ph.D. in Statistics from Yale University under the supervision of Andrew Barron and I completed my undergraduate coursework at the University of North Carolina at Chapel Hill where I obtained a B.S. in Mathematics.
My research uses tools and ideas from information theory, statistical physics, and applied probability as a framework for understanding modern, high-dimensional inference and estimation problems and complex machine learning tasks that are core challenges in the fields of current statistics and data science. The thrust of my research is in answering the questions like, Given a complex statistical problem, how much data, or information, is needed to solving it? How does one most effectively use data to gain insight on the problem at hand and how can we quantitatively describe the limitations of this insight? Can we develop and analyze the performance of computationally-efficient algorithms and procedures for statistical inference and estimation in these settings?
To this end, and in hopes of contributing meaningfully to the challenges faced by modern statisticians, I have focused my research endeavors in two overarching directions. The first is establishing a better understanding of the fundamental limits of statistical recovery in complex problems and designing computationally-efficient methods to perform at those limits. The second is establishing rigorous theoretical guarantees for the performance high-dimensional statistical estimation and inference procedures.