My research focuses on problems in diffusion geometry and Bayesian statistics, that are motivated by the open challenges of extracting stable and interpretable information from high-dimensional data. On the theory side, I build algorithms and probabilistic models on geometric objects for dimension reduction, inference, regression and related machine learning problems. On the applied side, I use my work on anatomical surfaces (typically, teeth and bones of primates) to gain insights about evolutionary processes. On the implementation side, I develop robust and easy-to-use software to bridge the gap between research and practice.
Shan, S., Kovalsky, S. Z., Winchester, J. M., Boyer, D. M., & Daubechies, I. aria DNE: A Robustly Implemented Algorithm for Dirichlet Energy of the Normal. Methods in Ecology and Evolution. (webpage)