Published papers: 'Online Target Q-learning with Reverse Experience Replay' (ICLR 2022), 'Efficient Methods for Online Multiclass Logistic Regression' (ALT 2022), 'The Skellam Mechanism for Differentially Private Federated Learning' (NeurIPS 2021), etc.; involved in projects: Machine Learning for Mechanical Ventilation Control.
Research Experience
Senior Research Scientist at Google AI Princeton; focused on optimization for machine learning during his PhD.
Education
PhD in Computer Science from Princeton University, advised by Elad Hazan; MS in Computer Science from the University of Illinois Urbana-Champaign, advised by Prof. Alexandra Kolla; Bachelors from the Computer Science and Engineering Department at IIT Bombay, advised by Prof. Abhiram Ranade.
Background
Research interests: Optimization for Machine Learning, with a focus on faster optimization methods for Deep Learning; Robust Online Control and Reinforcement Learning; privacy and optimization aspects of Federated Learning.
Miscellany
Personal links: CV, Google Scholar, Github, LinkedIn