Vidya Muthukumar is an Assistant Professor in the Schools of Electrical and Computer Engineering, and Industrial and Systems Engineering at Georgia Institute of Technology. Dr. Muthukumar’s broad interests are in game theory, online and statistical learning. She is particularly interested in designing learning algorithms that provably adapt in strategic environments, fundamental properties of overparameterized models, and fairness, accountability, and transparency in machine learning.
Dr. Muthukumar 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. She interned at IBM Research in the summer of 2018 as a Science for Social Good fellow. Before joining Georgia Tech, she spent a semester at the Simons Institute for the Theory of Computing as a research fellow for the program “Theory of Reinforcement Learning.” She is the recipient of a Simons-Berkeley Google Research Fellowship, IBM Science for Social Good Fellowship, and the UC Berkeley EECS Outstanding Course Development and Teaching Award. Dr. Muthukumar serves on the senior program committee for COLT 2021 and ALT 2022.
In her spare time, Dr. Muthukumar enjoys singing Carnatic vocal music, playing the piano, and long-distance cycling.
- May 2022: I’m presenting our recent work on the complexity of infinite-horizon general-sum stochastic games at the Simons Institute workshop on multi-agent RL.
March 2022: Received the Adobe Data Science Research Award with Ashwin Pananjady for our joint work on inverse reward learning from a bandit demonstrator!
- Feb 2022: I’m co-organizing a mentorship workshop in conjunction with ALT 2022 for senior undergraduates and all-year graduates. Schedule here!
- Feb 2022: I’m listed on the Class of 1934 CIOS Honor Roll: Student Recognition of Excellence in Teaching for the new course that I introduced in Fall 2021, ECE 8803: Online Decision Making in Machine Learning.
- Jan 2022: I’m a long-term participant this semester at the Simons Institute Spring 2022 program on “Learning and Games”.
- Jan 2022: Invited presentation at University of Michigan ECE’s Communication and Signal Processing Seminar.
- Jan 2022: Papers on inverse learning from an exploring demonstrator and harmless interpolation in kernel regression and classification accepted to AISTATS 2022. Thanks and special mention to lead authors (Wenshuo Guo and Andrew McRae respectively)!
- Dec 2021: Our work on equivalences between the multiclass SVM, one-vs-all SVM and minimum-2-norm interpolation will be presented at NeurIPS 2021. Thanks and congrats to my co-authors Ke Wang and Christos Thrampoulidis!
- Oct 2021: Our work on classification-vs-regression in overparameterized regimes is published in Journal of Machine Learning Research.
- Sept 2021: New survey paper on theory of overparameterized ML, jointly authored with Yehuda Dar and Rich Baraniuk. Comments are very welcome!