2026
IEEE Information Theory Society Goldsmith Lecturer
Selected as a 2026 Goldsmith Lecturer by the IEEE Information Theory Society.
Understanding the limits of statistical learning and the algorithms that reach them.
My research develops and analyzes algorithms for learning from high-dimensional data, using ideas from statistics, information theory, statistical physics, and applied probability.
About
I am an Associate Professor of Statistics in the Department of Statistics at Columbia University. I received my Ph.D. in Statistics from Yale University in 2016 under the supervision of Andrew Barron. I completed my undergraduate studies at the University of North Carolina at Chapel Hill, where I received a B.S. in Mathematics.
Selected highlights
NSF
Fundamental Limits of High-Dimensional Statistical Estimation
Principal Investigator, NSF DMS-2413828.
Editorial service
Associate Editor
Journal of the Royal Statistical Society, Series B; Bernoulli; and IEEE Transactions on Information Theory.
Teaching innovation
Columbia Provost's Teaching and Learning Innovation Grant
$8,000 award supporting the redesign of STAT UN1201: Calculus-Based Introduction to Statistics, with support from Columbia's Center for Teaching and Learning.
Research
High-dimensional statistics
Fundamental limits of inference, estimation, and regularization in modern high-dimensional models.
Approximate message passing
Precise theory for AMP and VAMP algorithms, including state evolution and non-i.i.d. designs.
Statistical-computational gaps
When statistically optimal procedures are computationally inaccessible, and how to characterize the gap.
Information theory & probability
Using information-theoretic, probabilistic, and statistical-physics ideas to study inference and learning.
