DeepAI AI Chat
Log In Sign Up

Scalars are universal: Gauge-equivariant machine learning, structured like classical physics

by   Soledad Villar, et al.

There has been enormous progress in the last few years in designing conceivable (though not always practical) neural networks that respect the gauge symmetries – or coordinate freedom – of physical law. Some of these frameworks make use of irreducible representations, some make use of higher order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), and permutations. Here we show that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincaré groups, at any dimensionality d. The key observation is that nonlinear O(d)-equivariant (and related-group-equivariant) functions can be expressed in terms of a lightweight collection of scalars – scalar products and scalar contractions of the scalar, vector, and tensor inputs. These results demonstrate theoretically that gauge-invariant deep learning models for classical physics with good scaling for large problems are feasible right now.


page 1

page 2

page 3

page 4


Hierarchical Learning in Euclidean Neural Networks

Equivariant machine learning methods have shown wide success at 3D learn...

Machine Learning Lie Structures Applications to Physics

Classical and exceptional Lie algebras and their representations are amo...

GeometricImageNet: Extending convolutional neural networks to vector and tensor images

Convolutional neural networks and their ilk have been very successful fo...

Parsimonious neural networks learn classical mechanics, its underlying symmetries, and an accurate time integrator

Machine learning is playing an increasing role in the physical sciences ...

Quaternion Product Units for Deep Learning on 3D Rotation Groups

We propose a novel quaternion product unit (QPU) to represent data on 3D...

Deep Learning of Turbulent Scalar Mixing

Based on recent developments in physics-informed deep learning and deep ...