Department of Electrical and Computer Engineering
Department of Statistical Science
My research interests include information theory, statistics, machine learning, and signal processing. I am particularly interested in fundamental questions concerning the amount of data needed for an inference or learning task, the representation of uncertainty in high-dimensional and complex spaces, and the gap between practical and combinatorial methods. My approach to research is highly interdisciplinary and builds upon ideas from engineering, statistics, mathematics, theoretical computer science, and statistical physics.
04/2021 -- Here is a recent talk on the The Information-Theoretic limits of the matrix tensor product model, which I presented at the NYU / ETH MAD+ Seminar.
04/2021 -- In Fall 2021 I'll be teaching STA 0 711: Probability and Measure Theory
06/2020 -- My work with S. Goldt, M. Mézard, F. Krzakala, and L. Zdeborová on Gaussian equivalence of generative models for learning with two-layer neural networks has been posted to arxiv.
06/2020 -- My work with J. Barbier on Information-theoretic limits of a multiview low-rank symmetric spiked matrix model was presented at ISIT 2020.
05/2020 -- My paper Information-Theoretic Limits for the Matrix Tensor Product has been posted to arxiv.
Galen Reeves joined the faculty at Duke University in Fall 2013, and is currently an Associate Professor with a joint appointment in the Department of Electrical Computer Engineering and the Department of Statistical Science. He completed his PhD in Electrical Engineering and Computer Sciences at the University of California, Berkeley in 2011, and he was a postdoctoral associate in the Departments of Statistics at Stanford University from 2011 to 2013. His research interests include information theory and high-dimensional statistics. He received the NSF CAREER award in 2017.