Data for Good Seminar: David W. Hogg, NYU and Flatiron Institute
Data for Good Seminars invite leading academics from around the world to share how they are using data to address societal challenges.
Hosted by the DSI Computing Systems for Data-Driven Science Center
Guest Speaker: David W. Hogg is Professor of Physics and Data Science in the Center for Cosmology and Particle Physics in the Department of Physics at New York University. He is also Group Leader for the Astronomical Data Group in the Center for Computational Astrophysics of the Flatiron Institute, and he has an affiliation with the Max-Planck-Institut für Astronomie.
DSI Computing Systems Center Chairs:
Qiang Du, Fu Foundation Professor of Applied Mathematics at the Department of Applied Physics and Applied Mathematics (APAM)
Martha Kim, Associate Professor of Computer Science
Computing Systems Center Website
Machine learning, but structured like physical law
Physical laws obey strict symmetries, such as rotational, translational, permutation, and coordinate symmetries, along with restrictions related to dimensions (or units). These can be enforced exactly by requiring models to be written according to geometric and algebraic rules. I demonstrate with toy examples that these ideas can be implemented simply, and that they help with accuracy and generalizability of existing machine-learning methods. More importantly these ideas might have an impact on interpretability, explainability, or symbolic approaches to learning with data. I’ll say a bit about causal structure too, since the strictly symmetric part of a data analysis is often hidden in a latent space that’s only observed indirectly. (Work with Soledad Villar, JHU and others.)