About me

I am a final-year graduate student in the Computer Science department at Princeton University, advised by Prof. Sanjeev Arora. My research focuses on understanding the effect of the model architecture and optimization algorithms on the generalization behavior of deep learning models. My past works have spanned across different research directions, like neural tangent kernels, feature learning, implicit bias of optimization algorithms, skill localization in large language models, efficient pre-training, and test time adaptive architectures.

Previously, I was a Research Fellow at Microsoft Research Lab - India where I was fortunate to work with Dr. Harsha Vardhan Simhadri and Dr. Navin Goyal on unsupervised techniques for word embeddings and theory of optimization and generalization guarantees for neural networks. Prior to the fellowship, I attended IIT Kharagpur where I obtained my B.Tech. in Computer Science and Engineering in 2018.