I’m broadly interested in stochastic modeling, machine learning, and computational statistics. In particular, much of my work focuses on contributing inferential tools in dependent, constrained, and missing data settings.
Currently, I am using majorization-minimization (a generalization of EM) to derive fast algorithms for tasks including clustering and estimation under novel non-convex penalties. I also develop latent variable approaches for inference in dynamic stochastic models, especially discrete valued Markov processes in continuous time such as branching processes and mechanistic compartmental models. Recently I am considering their extensions over spatial domains and networks, incorporating more flexible rules of behavior and interaction. My work primarily focuses on developing theory and methods, often driven by applications to systems biology and epidemiology. I am especially interested in likelihood-based formulations, and connections between Frequentist and Bayesian approaches derived from this perspective.
On the applications side, much of my work has focused on stochastic modeling and inference for hematopoiesis, the process of blood cell production. Recently, I’ve gotten interested in epidemiological data and in emergent data types from single-cell lineage tracking and sequencing.
A list of publications along with software is available here.