Vidya Muthukumar


PhD Student
Department of Electrical Engineering and Computer Science
University of California, Berkeley

vidya.muthukumar (at) eecs (dot) berkeley (dot) edu
264 Cory Hall

Berkeley Laboratory for Information and System Sciences (BLISS)


Preprint on online model selection for linear bandits.
Paper on robust commitments and partial reputation to appear at ACM Economics and Computation 2019.
Paper on harmless interpolation in noisy linear regression to appear at IEEE ISIT 2019.
Attended the iREDEFINE academic networking workshop with ECE Department Heads as UC Berkeley's student nominee.
Invited talk at Stanford DAWN seminar, March 2019.
Graduation Day talk at Information Theory and Applications Workshop.
Paper on robust model selection for online prediction to appear at AISTATS 2019.
Preprint on understanding unequal gender classification accuracy from facial images.
Invited talk at University of Washington ML seminar, October 2018.
Invited talk at Cornell ORIE Young Researchers’ Workshop, October 2018.
Co-instructed special topics course EE290S: Machine Learning For Sequential Decision Making Under Uncertainty, Fall 2018.

About me

I am a fifth year graduate student in the EECS Department at UC Berkeley, advised by Anant Sahai. My thesis committee members are Jean Walrand, Peter Bartlett, and Shachar Kariv.

I recently completed a wonderful internship at IBM Research AI as a Science for Social Good Fellow for the summer, primarily collaborating with Kush Varshney.

My broad interests are in game theory, online learning, statistics and reinforcement learning. I’m particularly interested in designing learning algorithms that provably adapt in strategic environments. I’m also intrigued by the implications of partial leader commitment in Stackelberg games. Some other topics I’ve worked on include theoretical and empirical studies of incentive mechanisms for spectrum sharing, and ranking from partial pairwise comparisons.

Recently, I co-instructed a special topics course with Prof. Sahai on sequential decision-making under uncertainty in Fall 2018. I TAed and co-designed the first full-scale offering of EE16A in Fall 2015 at UC Berkeley, and served as the co-president of Women in Computer Science and Electrical Engineering (WICSE) for the academic year 2016-17.