Biography

I am an assistant professor in the School of Electrical and Computer Engineering at Purdue University. Previously, I was a postdoc at Carnegie Mellon University working with Prof. Pradeep Ravikumar. I completed my Computer Science PhD at The University of Texas at Austin in 2017 advised by Prof. Inderjit Dhillon and Prof. Pradeep Ravikumar. I obtained my B.S. in Electrical Engineering from Georgia Institute of Technology with a minor in Computer Science. I was awarded the NSF Graduate Research Fellowship (NSF GRFP).

My research interests focus on the fundamentals of machine learning, probabilistic models, invertible deep learning, and explainable AI with an emphasis on generative models and density estimation. Currently, I am focused on creating the foundations for destructive deep learning, which is a local and forward-only optimization algorithm for deep models—in contrast to standard end-to-end optimization which is global and requires both forward and backward communication. Intuitively, destructive learning (or deconstructive learning) is similar in concept to reverse engineering patterns in data. I am also interested in explainable AI techniques both from an intrinsic viewpoint by creating more explainable methods (e.g., via destructive learning or self-explainable models) or from an extrinsic viewpoint by creating diagnostic tools to better understand models—e.g., what would the model predict if the input was changed in interesting ways?