I am a Research Associate in the Machine Learning and Optimization (MLO) team at Google Research India , working with Dr. Prateek Jain and Dr. Abhradeep Thakurta towards privacy-preserving optimization methods. I am broadly interested in developing robust machine learning methods and their mathematical foundations for scientific applications.
In May 2021, I graduated from the Indian Institute of Technology Kanpur (IIT Kanpur) with a B.Tech. in Computer Science and Engineering and a Minor in Cognitive Science. During my undergraduate studies, I have had the fortune to work with some of the best scientific minds around the globe. As part of E3@EPFL, I worked with Dr. Grigoris Chrysios and Prof. Volka Cevher in the previous summers on combining Unsupervised Domain Adaptation (UDA) and Class Incremental (CI) learning methods to improve the generalizability of classifiers. As an S.N. Bose Scholar, I worked with Dr. Florian Schafer and Prof. Animashree Anandkumar at Caltech during the summers of 2020 on the intersection of Game Theory/Mechanism Design and Deep Learning to develop zero-sum game strategies and obtain robust classifer models. Around the same time, I interned as a Software Engineer with Microsoft India for which I received a Pre-placement Offer (PPO). In the summer of 2019 summers, I worked under Prof. Djordje Jevdjic at the National University of Singapore (NUS) on a DNA-based archival storage tool, with a specific focus on designing and implementing a robust sub-quadratic time Clustering Algorithm.
I also spend time as a sign language interpreter and mentor people from the deaf and mute community on matters of financial planning.
B.Tech in Computer Science and Engineering with Minors in Cognitive Science, 2021
Indian Institute of Technology Kanpur
Supervisor: Prof. Dootika Vats, IIT Kanpur. We Explored the avenues of variance reduction methods such as Control Variates and their applications to Stochastic Gradient based Langevin Dynamics (SGLD), MCMC (SGMCMC) and Hamiltonian Monte Carlo (SGHMC) techniques.
Supervisor: Prof. Vipul Arora, IIT Kanpur. In this term report we presented our model for the speaker diarization problem and explained how one can leverage Transfer Learning to quickly learn a model at the expense of negligible performance loss as compared to a fully trained one.
Supervisor: Prof. Ketan Rejawat, IIT Kanpur. In this term report we eproduced and extended the empirical results of “On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization” and ”Accelerating Stochastic Gradient Descent For Least Squares Regression” by Kidambi et al.