I am an assistant professor at the Department of Statistics & Actuarial Science at the University of Waterloo. I completed my PhD in Statistics at the University of Michigan working with Prof. Yuekai Sun and Prof. Moulinath Banerjee. Prior to my PhD, I completed my undergraduate and masters studies at Indian Statistical Institute, Kolkata with a focus on mathematics and statistic

 

Research interests: I am broadly interested in the statistical foundations of data science. Some of my recent interests are:

  • Large Language Models: LLM routing [1], LLM alignment [1]
  • Distribution shift & transfer learning [1, 2, 3, 4], Performative prediction [1, 2]
  • Fairness & Interpretability in ML algorithms [1, 2, 3, 4, 5]
  • Missing data [1]

 

E-mail: smaity (at) uwaterloo (dot) ca

Recent News:

  • Our recent work "CARROT: A Cost Aware Rate Optimal Router" has been accepted to ICLR 2025 FM-Wild Workshop. 
  • Our recent work "Estimation with missing not at random binary outcomes via exponential tilts." on non-ignorable missing data has been posted on arxiv. 
  • Our recent work "CARROT: A Cost Aware Rate Optimal Router." on LLM-routing has been posted on arxiv. Also, our router model and SPROUT benchmark dataset has been released in huggingface community. 
  • Our paper "Microfoundation inference for strategic prediction." [arxiv-preprint] has been accepted in AISTATS 2025.
  • Our paper "Learning the distribution map in reverse causal in performative prediction." [arxiv-preprint] has been accepted in AISTATS 2025.
  • Our paper "Weak supervision performance evaluation via partial identification." [openreview] has been published in NeurIPS 2024 conference proceedings.