cs.LGNov 6, 2026

Enforcing Symmetries on Pre-trained ML Models for Physics

Authors: Wenjie Zhou, Valentino F. Foit, David W. Hogg, Soledad Villar

Organizations: Department of Physics and Astronomy, Johns Hopkins University, Baltimore, MD 21218, USA · Center for Cosmology and Particle Physics, Department of Physics, New York University, New York, NY 10003, USA · Max-Planck-Institut für Astronomie, Königstuhl 17, D-69117 Heidelberg, Germany · Center for Computational Astrophysics, Flatiron Institute, 162 Fifth Ave., New York, NY 10010, USA · 

Abstract

Post-hoc group averaging (or test-time augmentation) is a simple way to impose symmetry on a trained predictor without changing its architecture or retraining it. For finite and compact groups, averaging over a normalized Haar measure on the group gives the Reynolds operator: a canonical projection onto invariant or equivariant predictors with known non-increasing risk guarantees under certain assumptions. This paper provides numerical experiments on physics emulation models that demonstrate the effectiveness of the approach in this setting. We then extend this framework to non-compact group symmetries. For non-compact groups, the Haar measure cannot be normalized, so group averaging cannot be defined in the same way. We replace it with three alternatives: the Weyl unitary trick (which requires complexifying the space and extending the predictor), a data-dependent orthogonal projection (which involves a non-trivial optimization on the space of invariant or equivariant functions), and a frame averaging approach (which involves mapping each point to a set of orbit representatives). We illustrate the constructions theoretically and empirically on the unit-rescaling group and the Lorentz group. Our results show that in the non-compact case, the Weyl trick and frame averaging do not provide a consistent improvement over the baseline, except where the test data is out-of-distribution (an orders-of-magnitude improvement in this case) and, for the Weyl trick, in low-data regimes. The orthogonal projection can provide improvements in-distribution and out-of-distribution. We also observe that models trained directly on invariant features matched or beat the projection of an unconstrained one. We conclude that post-hoc symmetrization extends to non-compact groups, but it does not consistently outperform training a symmetric model.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. How unconstrained machine-learning models learn physical symmetries

    Mar 25, 2026Michelangelo Domina, Joseph William Abbott, Paolo Pegolo +2Equivariant Representation LearningPhysics-Based Simulation

  2. Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group

    Jun 2, 2026Hongbo WangWorld Models for RoboticsWorld Models

  3. Data Augmentation: A Fourier Analysis Perspective

    Jun 23, 2026Behrooz Tahmasebi, Melanie Weber, Stefanie JegelkaData AugmentationStatistical Learning Theory