Welcome!

I am a graduate student in the Department of Biostatistics at the University of Michigan. In the fall of 2023 I started my fifth (and final 🤞) year here in Ann Arbor.

📣 News

• 2023.12.14 - My paper on Generative causality: using Shannon’s information theory to infer underlying asymmetry in causal relations is now available on arXiv!
  In this paper, I propose a new framework where any causal link between putative cause and effect is generated by asymmetric information flow from one variable to another. Using an entropy-based coefficient, I capture said asymmetry in observational studies.
• 2023.11.29 - My paper on fastMI: a fast and consistent copula-based nonparametric estimator of mutual information is published by the Journal of Multivariate Analysis!
  In this paper, we develop a consistent and powerful estimator, called fastMI outperforms state-of-the-art estimators of MI with improved estimation accuracy and reduced run time for large data sets.
• 2023.11.07 - A technical report on Asymmetric predictability in causal discovery: an information theoretic approach is now available on arXiv!
  In this report, we present and information geometric causal discovery framework of “predictive asymmetry” to unearth latent directionality in data coming from observational studies.
• 2023.06.20 - Received the 2023 WNAR Best Student Paper Award (written category) for my work on asymmetric predictability in causal discovery.
• 2023.03.27 - Awarded the 2023 Rising Star Award by the University of Michigan for my work with STATCOM!
• 2023.03.18 - Selected as a recipient of a travel award for the CBMS Conference Foundations of Causal Graphical Models and Structure Discovery supported by the National Science Foundation (NSF DMS-2227849) and Texas A&M Institute for Applied Mathematics and Computational Science (IAMCS).
• 2023.02.27 - Awarded the Rackham Predoctoral Fellowship for 2023-24!

📖 Research

Broadly, I am interested in scaleable and flexible statistical models for design and analysis of biomedical studies and their applications to medical or social science and public policy. The research that I work on include Bayesian methods as well as classical semi- and non-parametric approaches. I love challenges in statistical computing and spend most of my time rubber-ducking my code to myself.

Over the years I have had extensive experience with C++, Python, R and UNIX. Through my research and internships I have learnt to combine computational expertise with statistical knowledge (e.g. data mining, regression, clustering, decision trees, factor analysis, neural networks) to handle domain-specific problems. I am proficient in working with large data sets using strategies like parallelization, MapReduce, and memory-efficient data.