- This event has passed.
ESE Fall Seminar – “Approximate symmetries in machine learning”
November 9, 2023 at 11:00 AM - 12:00 PM
In this talk, we explain different roles that symmetries and approximate symmetries can play in machine learning models. We define approximately equivariant graph neural networks and we show a bias-variance tradeoff when selecting the symmetries to enforce. We explain how to see equivariant functions as gradients of invariant functions, and we show how to use these ideas in self-supervised learning.
Soledad Villar
Assistant Professor of Applied Mathematics & Statistics, Johns Hopkins University
Soledad Villar is an Assistant Professor of Applied Mathematics and Statistics at Johns Hopkins University. She received her PhD in mathematics in 2017 from UT Austin and was later a research fellow at the Simons Institute in UC Berkeley, and a Moore-Sloan Research Fellow at NYU. Her research is in mathematical data science, including mathematical theory of deep learning, representation learning, and applications. Her work has been funded by NSF, The Simons Foundation, ONR, and EOARD.