About me
Hi! I am Aditya. I am a Ph.D. candidate in Statistics at Stanford University, fortunate to be advised by Stefan Wager and Dominik Rothenhäusler.
My research focuses on problems in causal inference, statistical learning, and optimization. I am currently working on causal inference in dynamic systems and causal inference under distribution shift.
I will be on the 2026-27 job market.
Outside of research, I enjoy traveling, photography, movies, and chess. Before starting my Ph.D., I used to mentor high school students for Mathematical Olympiads and similar competitions; check out this old blog for resources.
Selected research
Dynamic Thresholding Designs
We study thresholding designs in general dynamic systems, and show that simple reduced-form characterizations remain available for a relevant causal target, namely a dynamic marginal policy effect at the treatment threshold.
Specification-robust Causal Inference
When it is unclear which covariates to adjust for, we provide valid inference for a reweighted population when at least one of the candidate adjustment sets is valid.
PLRD: Partially Linear Regression Discontinuity Inference
For treatment rules with an eligibility threshold, PLRD delivers narrow yet reliable confidence intervals for the effect at the threshold by solving a minimax problem.
Other roles
I help organize the Online Causal Inference Seminar, a weekly seminar on causal inference with participants from all over the world.