Equivariance and generalization in neural networks

Abstract

The crucial role played by the underlying symmetries of high energy physics and lattice field theories calls for the implementation of such symmetries in the neural network architectures that are applied to the physical system under consideration. In these proceedings, we focus on the consequences of incorporating translational equivariance among the network properties, particularly in terms of performance and generalization. The benefits of equivariant networks are exemplified by studying a complex scalar field theory, on which various regression and classification tasks are examined. For a meaningful comparison, promising equivariant and non-equivariant architectures are identified by means of a systematic search. The results indicate that in most of the tasks our best equivariant architectures can perform and generalize significantly better than their non-equivariant counterparts, which applies not only to physical parameters beyond those represented in the training set, but also to different lattice sizes.

arXiv comment8 pages, 7 figures, proceedings for the 14th Quark Confinement and the Hadron Spectrum Conference (vConf2021)

References in corpus (10)

• Machine learning phases of matter
• Worm algorithms for classical statistical models
• Equivariant flow-based sampling for lattice gauge theory
• Gauge Equivariant Convolutional Networks and the Icosahedral CNN
• Sampling using $SU(N)$ gauge equivariant flows
• Regressive and generative neural networks for scalar field theory
• Lattice study of the Silver Blaze phenomenon for a charged scalar phi-4 field
• Machine learning action parameters in lattice quantum chromodynamics
• Machine Learning Estimators for Lattice QCD Observables
• Generalization capabilities of translationally equivariant neural networks

Cited by in corpus (3)

• A rotation-equivariant graph neural network for learning hadronic SMEFT effects
• Equivariant neural networks for robust $\text{CP}$ observables
• Large Language Models -- the Future of Fundamental Physics?