I am a Research Fellow at Microsoft Research Lab - India mentored by Dr. Praneeth Netrapalli and Dr. Prateek Jain. I am a part of the Provable Non-convex Optimization for Machine Learning Problems project group.
My interests are in aspects of Large-Scale Optimization, Random Matrix theory and Statistical Learning theory that arises in fundamental Machine Learning problems.
Our recent work, Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds has been accepted for a Spotlight presentation at NeurIPS 2018. Currently I am trying to understand the trade-offs between optimization and generalization in simple Neural Networks. Other topic that have caught my recent attention are Reproducing Kernel Hilbert Space theory, Manifold Optimization and Gradient flows in the space of probability measures. I am also interested in High dimensional geometry, Statistics, Analysis and areas that require geometric thinking.
I will be joining Paul G. Allen School of Computer Science and Engineering at University of Washington as a graduate student from Fall 2019. You can find my resume here.