Description
Ethan is an applied mathematician with experience in control, optimization, modeling, and machine learning. He is interested in leveraging the tools and successes of data science to push the boundaries of complexity and scale possible within scientific computing. Within modeling, his interests are in methods to learn uncertain physics in complex systems from data, and to merge domain knowledge with machine learning for fast accurate predictions. Within optimization, his interests are in the use of differentiable programming to greatly increase the solution speed for complex and large scale problems.