Dr. Soledad Villar -- Exploiting symmetries in machine learning models

Chalmers AI4Science seminar held May 11, 2023 with guest speaker Dr. Soledad Villar from Johns Hopkins University.

Talk Abstract
Any representation of data involves arbitrary investigator choices. Because those choices are external to the data-generating process, each choice leads to an exact symmetry, corresponding to the group of transformations that takes one possible representation to another. These are the passive symmetries; they include coordinate freedom, gauge symmetry and units covariance, all of which have led to important results in physics. Our goal is to understand the implications of passive symmetries for machine learning: Which passive symmetries play a role (e.g., permutation symmetry in graph neural networks)? What are dos and don’ts in machine learning practice? We assay conditions under which passive symmetries can be implemented as group equivariances. We also discuss links to causal modeling, and argue that the implementation of passive symmetries is particularly valuable when the goal of the learning problem is to generalize out of sample.

Speaker Biography
Dr. Soledad Villar is an assistant professor of applied mathematics and statistics at Johns Hopkins University. Currently she is a visiting researcher at Apple Research in Paris. She was born and raised in Montevideo, Uruguay.