I am the Harold R. and Mary Anne Nash Early Career Professor and Assistant Professor in the School of Electrical and Computer Engineering and H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology. I received the B.Tech (with honors) degree from the Indian Institute of Technology, Madras and the Ph.D. degree in Electrical Engineering from University of California, Berkeley. Before joining Georgia Tech, I spent a semester at the Simons Institute for the Theory of Computing as a research fellow for the program “Theory of Reinforcement Learning.”
My broad interests are in game theory, online and statistical learning. I am particularly interested in designing learning algorithms that provably adapt in strategic environments, fundamental properties of overparameterized models, and the foundations of multi-agent decision-making. In my spare time, I enjoy singing Carnatic vocal music, playing the piano, and long-distance cycling.
See here for a more formal bio in the third person.
Recent News
-
- September 2026: I had a great time presenting our empirical and theoretical perspectives on distributional robustness of neural network learning at the UPenn ASSET Seminar and the CMU ML/AI Seminar.
- August 2026: Welcome to ARC postdoctoral fellow John Lazarsfeld!
- June 2026: Kuo-Wei Lai is presenting the work he led on characterizing the implicit bias of shallow ReLU networks on high-dimensional data at COLT 2026. Congratulations to Kuo-Wei and collaborators Guanghui Wang and Molei Tao! 🙂
- May 2026: Our work on exploring plausible hypotheses for the success of last-layer retraining in distributional robustness is published in Transactions on Machine Learning Research. Congratulations to student authors John Collins Hill, Tyler LaBonte and Xinchen Zhang!
- May 2026: A huge congratulations to my students Chiraag Kaushik, Kuo-Wei Lai and Tyler LaBonte on their PhD graduations!!! 🙂
- April 2026: I had a great time presenting our work on kernel interpolation and approximation at the Harvard Statistics Colloquium.
- March 2026: I presented our recent work on a general technique for approximating empirical high-dimensional kernel matrices (remotely) at the Oberwolfach workshop on “Modern and Emerging Phenomena in Machine Learning”.
- February 2026: I enjoyed presenting our work on the surprising last-iterate convergence of exponential weights in 2×2 symmetric general-sum games at Information Theory and Applications (ITA) 2026 and Algorithmic Learning Theory (ALT) 2026. This work won the best student paper award at ALT 2026. A big congratulations to all my co-authors and especially lead student author Guanghui Wang!
- December 2025: Our work on the impact of general training losses in high dimensions, led by Kuo-Wei Lai, is published in Journal of Machine Learning Research. Congratulations, Kuo-Wei!
- October 2025: Our faster rates for generic and adversarially robust optimization methods, achieved through an online learning/game approach and led by Guanghui Wang, are published in Mathematical Programming Series B (special issue on Optimization for Machine Learning). Congratulations, Guanghui!
