My research interests are broadly outlined below.
(a) OOD Generalization, Uncertainty Quantification: characterizing and improving ML model behavior under distribution shifts.
(b) Knowledge-driven: leveraging external knowledge to improve zero shot, few shot learning.
(c) Generative Modeling & Imaging: solving ill-posed inverse imaging problems with novel generative priors.
(d) Sim2Real with ML: Understanding the challenges of transferring, generalizing ML models trained on simulation data to the real world
OUTREACH & OTHER EFFORTS:
At LLNL, I also lead the Open Data Initiative with the goal of releasing LLNL’s high impact scientific datasets for machine learning — so far, we have 10+ datasets and counting!
AI.gov recently cited this effort under “DATA RESOURCES FOR AI R&D”!
I also serve on the program committees for several ML and vision venues (NeurIPS, CVPR, ICLR, ICCV, ICML, AAAI).
I got my PhD, from Arizona State University (ASU) working with Prof. Pavan Turaga. In grad school, I developed tools spanning computer vision, machine learning, and Riemannian Geometry to improve our understanding of human movement and activity, when observed through various visual and non-visual sensors.
My PhD thesis is available for download here — Statistical and dynamical modeling of Riemannian trajectories with application to human movement analysis
I also received my M. S. (2012) from ASU, and my B. Tech (2010) from National Institute of Technology Karnataka (NITK), consistently ranked among the top 10 engineering schools in India.
Prior to that I spent two years of high school in Chennai, India and grew up in my hometown — Secunderabad, India. In all I have lived in, and am associated with, 6 cities across India and the US.