White is an aerospace engineer turned applied machine learning researcher. After her M.S. in aerospace engineering, I invented and patented a method for eliminating transonic flutter in turbomachinery at Honeywell. While at Stanford, she developed two novel machine learning methods for faster and more accurate reduced order models. For her dissertation, White designed several neural network architectures that are biased to break problems into parts while learning to make aerodynamics predictions from very few examples.
Generally, White want to understand how to automatically draw boundaries and clusters in undifferentiated spatial and temporal data in a way that is useful for prediction. She expect to graduate June 2020.