Ashwin Pananjady


Simons-Berkeley Research Fellow
Program on Probability, Geometry, and Computation in High Dimensions
Simons Institute for the Theory of Computing
University of California, Berkeley
Google Scholar Page

ashwinpm (at) berkeley (dot) edu


September 2020: Paper taking a game-theoretic approach to preference learning along multiple criteria to appear in NeurIPS 2020
September 2020: Talk at the Columbia Statistics seminar
September 2020: Paper on instance-dependent guarantees for policy evaluation to appear in IEEE Transactions on Information Theory
September 2020: Preprint on permutation-based models for multi-way comparisons
August 2020: Early career speaker at the Bernoulli-IMS One World Symposium
August 2020: Graduated from Berkeley! Here is a link to my dissertation
April 2020: Excited to be joining ISyE and ECE at Georgia Tech as assistant professor in Spring 2021
April 2020: Received the David J. Sakrison Memorial Prize from the EECS department, UC Berkeley for my dissertation research
March 2020: Preprint on “model-free”, instance-optimal policy evaluation

About me

I am a research fellow at the Simons Institute as part of the program on Probability, Geometry, and Computation in High Dimensions. In Spring 2021, I will be joining ISyE and ECE at Georgia Tech as assistant professor. I received my PhD in EECS at UC Berkeley, and was advised by Martin Wainwright and Thomas Courtade. Before coming to Berkeley, I graduated with a B.Tech in Electrical Engineering from the Indian Institute of Technology (IIT) Madras.

My research is centered around the theoretical and methodological aspects of drawing inferences from large, noisy data sets, and builds upon ideas rooted in statistics, optimization, and information theory. I like thinking about the statistical and computational trade-offs of estimation in both the passive and sequential settings when the underlying object to be estimated has some interesting geometric structure. My recent work has focused on various nonparametric problems in high-dimensional statistics, iterative optimization algorithms, and statistical questions in reinforcement learning.