I am a CS PhD candidate at the University of Southern California, advised by Prof. Vatsal Sharan of the USC CS Theory Group. I am also fortunate to work closely with Prof. Christos Thrampoulidis and Prof. Mahdi Soltanolkotabi, and intern with Hidenori Tanaka’s group, co-affiliated with PHI, NTT and CBS, Harvard.My research focuses on making foundational advances to improve our understanding of deep learning-based systems and make them more reliable and trustworthy. I use both theoretical tools and empirical insights to analyze the optimization and generalization dynamics of ML models, improve their robustness to distributional shifts, and, more recently, develop faithful abstractions of ML model behavior.Previously, I was a (remote) Visiting Researcher at CVPR Unit, ISI Kolkata, advised by Prof. Umapada Pal and Prof. Saumik Bhattacharya, working on deep metric learning. Before that, I graduated from IIT Roorkee with a bachelor’s in ECE. For my thesis, I worked on generative adversarial network-based methods for compressive sensing MRI reconstruction, under the guidance of Prof. Saumik Bhattacharya and Prof. PM Pradhan. I also interned at Northwestern University as an SN Bose Scholar in the summer of 2019.