I am an 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
- April 2024: Our work on the good, bad and ugly sides of data augmentation, led by Chi-Heng (Henry) Lin and Chiraag Kaushik, is published at Journal of Machine Learning Research. Congratulations, Henry and Chiraag!
- Feb 2024: I’m chairing the second ITALT symposium that will be co-located with the annual Information Theory and Applications Workshop, and the Algorithmic Learning Theory Conference in San Diego! Details about the symposium here.
- Dec 2023: My students Guanghui Wang and Tyler LaBonte presented their papers on faster margin maximization rates for generic optimization methods, and towards last-layer retraining for group robustness with fewer annotations at NeurIPS 2023. Congratulations, Guanghui and Tyler!
- Dec 2023: I will be co-presenting a tutorial at NeurIPS 2023 on Dec 11 on “Reconsidering overfitting in the age of overparameterized models” with Spencer Frei and Fanny Yang. Schedule of all tutorials here!
- Oct 2023: We had a wonderful experience organizing Learning Theory Alliance’s annual mentorship workshop! Thanks to my amazing co-organizers and all of our invited speakers, mentors and volunteers.
- Oct 2023: My student Guanghui Wang and I presented our work on adaptive oracle-efficient online learning at the INFORMS Annual Meeting.
- Oct 2023: Our work on benign overfitting in multiclass classification (joint with Ke Wang and Christos Thrampoulidis) is now published in IEEE Transactions on Information Theory.
- Sept 2023: I will be speaking about our group’s efforts on understanding interpolation in classification and regression tasks at the Mini-Workshop: Interpolation and Over-parameterization in Statistics and Machine Learning at Mathematisches Forschungsinstitut Oberwolfach.
- Summer and Fall 2023: Enjoyed giving talks at SIAM OP23, JSM 2023, the Math-ML seminar at MPI/UCLA, and Deepmath 2023 on our work on equivalences of loss functions at training in the overparameterized regime.
- April 2023: Congratulations to my student Kuo-Wei Lai for winning the 2023 Outstanding ECE Graduate Teaching Assistant Award!