Reese Pathak
Reese Pathak photo Ph.D. student

Department of Electrical Engineering and Computer Science (EECS)
University of California, Berkeley

I am a PhD student at the University of California, Berkeley, in the Department of Electrical Engineering and Computer Science (EECS). My advisors are Martin Wainwright and Mike Jordan. I am affiliated with the Berkeley AI Research (BAIR) lab.

My research interests span continuous optimization and high-dimensional statistics (and the many connections between these areas). More specifically, my recent work attempts to address–from a theoretical point of view–the statistical challenges encountered in modern learning problems: buzz-words include "distribution shift," "covariate shift," and "transfer learning."

Publications

2023

Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints
with Martin J. Wainwright and Lin Xiao.
[ arXiv ]

2022

Optimally tackling covariate shift in RKHS-based nonparametric regression
with Cong Ma and Martin J. Wainwright.
[ arXiv ] [ Annals of Statistics (to appear, 2023+) ]

A new similarity measure for covariate shift with applications to nonparametric regression
with Cong Ma and Martin J. Wainwright.
[ arXiv ] [ ICML 2022 (proceedings) (slides) (poster) (long oral) ]

2021

Cluster-and-Conquer: A Framework For Time-Series Forecasting
with Rajat Sen, Nikhil Rao, N. Benjamin Erichson, Michael I. Jordan, and Inderjit S. Dhillon.
[ arXiv ]

2020

Weighted matrix completion from non-random, non-uniform sampling patterns
with Simon Foucart, Deanna Needell, Yaniv Plan, and Mary Wootters.
[ arXiv ] [ IEEE Transactions on Information Theory ]

FedSplit: an algorithmic framework for fast federated optimization
with Martin J. Wainwright.
[ arXiv ] [ NeurIPS 2020]

On identifying and mitigating bias in the estimation of the COVID-19 case fatality rate
with Anastasios Angelopoulos, Rohit Varma, and Michael I. Jordan.
[ arXiv ] [ Harvard Data Science Review ] [ code ]


Teaching

Previous

Note that the links below typically reflect current course offerings, and therefore do not represent the course that I helped teach. Nonetheless, I have included the links in case the context is helpful.

UC Berkeley

Stanford University


Contact

Cory Hall, BLISS Lab
pathakr@berkeley.edu
http://www.cs.berkeley.edu/~pathakr/