About me

I am on the academic job market (2026–27).

I am currently a Founder’s Postdoctoral Fellow in the Department of Statistics at Columbia University. During my postdoc, I have had the opportunity to collaborate with Rina Foygel Barber, Samory Kpotufe, Edward Kennedy, Sivaraman Balakrishnan, and Larry Wasserman.

I completed my PhD in Statistics at the Department of Statistics and Data Science, Wharton School of the University of Pennsylvania, where I was advised by T. Tony Cai. During my PhD, I also worked closely with Eugene Katsevich. Prior to that, I completed both my Bachelor’s and Master’s degrees at the Indian Statistical Institute.

My research centers on two broad themes:

• Learning under privacy constraints: I have worked extensively on privacy-accuracy tradeoffs for nonparametric problems in federated settings — regression, classification, hypothesis testing, and functional data estimation — as well as the cost of adaptation under differential privacy. I have also studied privacy in other settings, such as when data on different variables is held by different parties (e.g., estimating correlation), and in structured data problems including network membership estimation, peer effect estimation via Ising models, and ranking from pairwise comparisons. A related thread is stability-accuracy tradeoffs, which are deeply connected to privacy.

• Learning with auxiliary data: How can we exploit auxiliary information to learn better? This includes heterogeneous transfer learning and the cost of adaptation, learning from shared representations, transfer learning for unsupervised problems, and using black-box predictors for testing and inference. This is the focus of much of my current work.

I have also worked on problems in multiple testing, variable selection, and conditional independence testing.