Soledad Villar, Ph.D.
Assistant Professor, Applied Mathematics, Johns Hopkins University
Soledad Villar is an Assistant Professor of Applied Mathematics and Statistics at Johns Hopkins University. Her research currently focuses on designing and analyzing machine learning models that exploit the geometric structure of the data or satisfy symmetries, such as graph neural networks and equivariant machine learning. Many of these symmetries arise from physical law and are implemented with techniques from classical invariant theory.