John von Neumann Fellow
I am a mathematician interested in basic and applied research questions that arise in the contexts of data science, nonlinear partial differential equations, and scientific machine learning. Lately, my focuses are primarily on (1) developing structure-informed surrogate models for the efficient approximation of large-scale systems, and (2) designing neural network architectures which better respect the underlying physical or mathematical properties of their training data. In each case, this involves formulating models with strong inductive biases, enabling practical benefits such as greater stability, easier training, and more realistic results at prediction time.
I joined Sandia in August 2022 as the John von Neumann Fellow in computational science.
Ph.D. in Mathematics, Texas Tech University, 2019
See my personal website.