I am a Staff Research Scientist in the National Security Sciences Directorate at Oak Ridge National Laboratory. My research interests include explainable AI, machine learning, computational imaging, optimization, and mathematical modeling. I am the recipient of research awards including the 2020 SIAM Imaging Sciences Best Paper Prize and the 2018 IEEE Signal Processing Society Young Author Best Paper Award.
Previously, I was Assistant Vice President of Quantitative Analytics at Wells Fargo in San Francisco. At Wells Fargo, I led the development of explainable machine learning algorithms for a variety of applications including financial crimes detection / anomaly detection, credit scoring, fraud detection, and loan loss forecasting.
I hold a PhD in electrical engineering from Purdue University, where my thesis advisor was Prof. Charles Bouman. At Purdue, I was funded by the Air Force Office of Scientific Research, MURI, and the Showalter Foundation to work on inverse imaging problems ranging from image super-resolution, tomography, and electron microscopy to image denoising, inpainting, and sparse image interpolation. My work was instrumental in developing the widely-used "Plug & Play Priors" framework which is a flexible distributed optimization technique to incorporate state-of-the-art algorithms (such as convolutional neural networks (CNNs), auto-encoders, BM3D/BM4D, non-local means, and K-SVD) as Bayesian prior models for regularized inversion. During my masters, I worked on high-speed cryptography algorithms for modular arithmetic. I am from the wonderful city of Bangalore in south India - where I earned my undergraduate degree in Telecommunications Engineering.