Hi! I’m a third-year Ph.D. student at UC San Diego, where I’m extremely fortunate to be advised by Arya Mazumdar.
I work on statistical learning theory, mostly on high-dimensional estimation from coarse or unreliable observations. I’m drawn to fundamental questions that are grounded in practical phenomena, like when simple algorithms work for reasons we cannot yet explain, or when a problem seems hard in general but is tractable on the instances we care about.
Before grad school, I had the privilege of spending three years at Microsoft Research India, working with Satya Lokam on privacy-preserving machine learning.
Please feel free to reach out at pmukherjee[at]ucsd[dot]edu
Selected papers
Following the convention in theoretical computer science, authors are listed alphabetically by last name.
-
On the Role of Normalization in Binary Iterative Hard Thresholding for 1-bit Compressed SensingACM–SIAM Symposium on Discrete Algorithms (SODA), 2027Paper
-
Rare-Tail Statistics For Learning Biased Gaussian Halfspaces with Label NoiseAdvances in Neural Information Processing Systems (NeurIPS), 2026Paper
-
On the Query Complexity of Training Data Reconstruction in Private LearningPreprint, 2023Paper
For a complete list, see my Google Scholar profile.