About me

I am currently a Founder’s Postdoctoral Fellow in the Department of Statistics at Columbia University. 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. Prior to that, I completed both my Bachelor’s and Master’s degrees at the Indian Statistical Institute.

My current research centers on the foundations of reliable modern statistical learning: stability–accuracy tradeoffs, the cost of adaptation under privacy constraints and distribution shift, and learning with shared representations. I’m also interested in inference with predictions: how to optimally use predictive models for valid and powerdul uncertainty quantification. During my PhD, I worked on minimax-optimal high-dimensional and nonparametric methods for distributed/federated inference under heterogeneous differential privacy constraints, with applications including functional estimation and nonparametric regression. I also collaborated with Eugene Katsevich on high-dimensional inference, variable selection, and conditional independence testing.