Ph.D. student Advisors: Michael I. Jordan and Martin J. Wainwright |

I am a PhD student in Computer Science at UC Berkeley, where I am a member of the Berkeley AI Research (BAIR) lab. Previously, I was an undergraduate at Stanford University.

My research interests are diverse and span high-dimensional statistics, optimization, and machine learning. Recently, I have been working on developing the foundations for learning under distribution shift (transfer learning) and random design nonparametrics. This work is motivated by contemporary applications, such as those arising in causal inference and federated learning.

Papers are ordered chronologically by date of initial announcement.

**Data-adaptive tradeoffs among multiple risks in distribution-free prediction**

with Drew T. Nguyen, Anastasios N. Angelopoulos, Stephen Bates, Michael I. Jordan.

[ arXiv ]

**On the design-dependent suboptimality of the Lasso**

with Cong Ma.

[ arXiv ]

**Transformers can optimally learn regression mixture models**

with Rajat Sen, Weihao Kong, and Abhimanyu Das.

[ arXiv ]
[ ICLR 2024 ]

**Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints**

with Martin J. Wainwright and Lin Xiao.

[ arXiv ]
[ Annals of Statistics (accepted, 2024+) ]

**Optimally tackling covariate shift in RKHS-based nonparametric regression**

with Cong Ma and Martin J. Wainwright.

[ arXiv ]
[ Annals of Statistics ]

**A new similarity measure for covariate shift with applications to nonparametric regression**

with Cong Ma and Martin J. Wainwright.

[ arXiv ]
[ ICML 2022 (long oral) |
slides |
poster
]

**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 ]

**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 ]

Previous teaching experience is listed below. Note that the links, when available, refer to current course offerings. I use the term TA to indicate the role of a teaching assistant (formally referred to as GSI at UC Berkeley).

**UC Berkeley**

Stat 210B (Mathematical Statistics): TA for Spring 2021.

**Stanford University**

EE 364a (Convex Optimization): Instructor for Summer 2017; TA for Winter 2017, 2018.

EE 104 (Introduction to Machine Learning): TA for Spring 2018.

EE 103 (Introduction to Matrix Methods): TA for Fall 2016, 2017, 2018.

CS 106{A,B,X}: Introductory data structures and algorithms sequence. TA for many quarters.

pathakr@berkeley.edu

http://www.cs.berkeley.edu/~pathakr/

© Reese Pathak. Last modified: September 16, 2024.