Jul 6 – 8, 2021
Europe/Zurich timezone

Symmetry Discovery with Deep Learning

Jul 8, 2021, 9:40 AM


Krish Desai (University of California, Berkeley)


Symmetries are a fundamental property of functions applied to datasets. A key function for any dataset is the probability density, and the corresponding symmetries are often referred to as the symmetries of the dataset itself. We provide a rigorous statistical notion of symmetry for a dataset, which involves reference datasets that we call inertial in analogy to inertial frames in classical mechanics. Then, we construct a novel approach to automatically discover symmetries from a dataset using a deep learning method based on an adversarial neural network. We show how this model performs on simple examples and provide a corresponding analytic description of the loss landscape. Symmetry discovery may lead to new insights and can reduce the effective dimensionality of a dataset to increase its effective statistics.

Affiliation Department of Physics, University of California, Berkeley, Physics Division, Lawrence Berkeley National Laboratory,
Academic Rank PhD Student

Primary authors

Ben Nachman (Lawrence Berkeley National Lab. (US)) Krish Desai (University of California, Berkeley) Jesse Thaler (MIT)

Presentation materials