Vidya Muthukumar

 

Simons-Berkeley Google Research Fellow
Theory of Reinforcement Learning Program
Simons Institute, UC Berkeley

vidya.muthukumar (at) berkeley (dot) edu

Affiliations:
Simons Institute for the Theory of Computing, UC Berkeley

News

Excited to be starting as an Assistant Professor in the ECE and ISyE departments of Georgia Tech in January 2021!
Nov 2020: Preprint on online model selection for reinforcement learning with function approximation.
Oct 2020: From the Simons Institute newsletter: my article on ‘‘Inside the Program: Theory of Reinforcement Learning“.
Oct 2020: Invited talk at Google Research.
Sept 2020: Preprint on high-probability equivalences between the max-margin SVM and least-norm interpolation in high dimensions.
August 2020: Graduated from UC Berkeley EECS! Here is a link to my doctoral dissertation.
May 2020: Preprint comparing classification and regression tasks in highly overparameterized regimes.
March 2020: Paper on harmless interpolation in noisy linear regression to appear in IEEE Journal of Selected Areas in Information Theory, special issue on ‘‘mathematics of deep learning”.

About me

I am a Simons-Berkeley Google Research Fellow at the Theory of Reinforcement Learning Program, Fall 2020. I just completed my PhD in EECS at UC Berkeley, where I was advised by Anant Sahai. My broad interests are in machine learning, game theory, mechanism design and information theory. I am interested in designing algorithms that provably adapt in dynamic and strategic environments, and I additionally seek a foundational understanding of the accuracy and transparency of modern machine learning.

In January 2021, I will be joining the Schools of Electrical and Computer Engineering and Industrial and Systems Engineering at Georgia Institute of Technology as an assistant professor.

Selected publications

  • Vidya Muthukumar, Kailas Vodrahalli, Anant Sahai: Harmless interpolation of noisy data in regression
    Shorter version at IEEE ISIT 2019, to appear in Journal for Selected Areas in Information Theory, inaugural special issue on “Deep Learning: Mathematical Foundations and Applications to Information Science”.

Teaching and service

Recently, I co-instructed a special topics course with Anant Sahai on sequential decision-making under uncertainty in Fall 2018 in UC Berkeley's EECS department. I served as the co-president of Women in Computer Science and Electrical Engineering (WICSE) for the academic year 2016-17.