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

• URL: http://arxiv.org/abs/2106.06610v1
• Date: Fri, 11 Jun 2021 20:51:38 GMT
• Title: Scalars are universal: Gauge-equivariant machine learning, structured like classical physics
• Authors: Soledad Villar (JHU), David W.Hogg (Flatiron, NYU), Kate Storey-Fisher (NYU), Weichi Yao (NYU), Ben Blum-Smith (NYU)
• Abstract summary: neural networks that respect the gauge symmetries -- or coordinate freedom -- of physical law. We show that it is simple to parameterize universally approximating functions that are equivariant under these symmetries. These results demonstrate theoretically that gauge-invariant deep learning models for classical physics with good scaling for large problems are feasible right now.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 Poincar\'e 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.

Related papers

• Learning equivariant tensor functions with applications to sparse vector recovery [5.557442038265024]
  We focus on equivariant functions with respect to the diagonal action of the Lorentz and symplectic groups. Our goal behind these characterizations is to define equivariant machine learning models.
  arXiv  Detail & Related papers  (2024-06-03T17:32:43Z)
• Explainable Equivariant Neural Networks for Particle Physics: PELICAN [51.02649432050852]
  PELICAN is a novel permutation equivariant and Lorentz invariant aggregator network. We present a study of the PELICAN algorithm architecture in the context of both tagging (classification) and reconstructing (regression) Lorentz-boosted top quarks. We extend the application of PELICAN to the tasks of identifying quark-initiated vs.gluon-initiated jets, and a multi-class identification across five separate target categories of jets.
  arXiv  Detail & Related papers  (2023-07-31T09:08:40Z)
• Generative Adversarial Symmetry Discovery [19.098785309131458]
  LieGAN represents symmetry as interpretable Lie algebra basis and can discover various symmetries. The learned symmetry can also be readily used in several existing equivariant neural networks to improve accuracy and generalization in prediction.
  arXiv  Detail & Related papers  (2023-02-01T04:28:36Z)
• PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics [64.5726087590283]
  We present a machine learning architecture that uses a set of inputs maximally reduced with respect to the full 6-dimensional Lorentz symmetry. We show that the resulting network outperforms all existing competitors despite much lower model complexity.
  arXiv  Detail & Related papers  (2022-11-01T13:36:50Z)
• Equivariant Graph Mechanics Networks with Constraints [83.38709956935095]
  We propose Graph Mechanics Network (GMN) which is efficient, equivariant and constraint-aware. GMN represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency.
  arXiv  Detail & Related papers  (2022-03-12T14:22:14Z)
• Generalization capabilities of neural networks in lattice applications [0.0]
  We investigate the advantages of adopting translationally equivariant neural networks in favor of non-equivariant ones. We show that our best equivariant architectures can perform and generalize significantly better than their non-equivariant counterparts.
  arXiv  Detail & Related papers  (2021-12-23T11:48:06Z)
• Equivariant vector field network for many-body system modeling [65.22203086172019]
  Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers. We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
  arXiv  Detail & Related papers  (2021-10-26T14:26:25Z)
• Frame Averaging for Invariant and Equivariant Network Design [50.87023773850824]
  We introduce Frame Averaging (FA), a framework for adapting known (backbone) architectures to become invariant or equivariant to new symmetry types. We show that FA-based models have maximal expressive power in a broad setting. We propose a new class of universal Graph Neural Networks (GNNs), universal Euclidean motion invariant point cloud networks, and Euclidean motion invariant Message Passing (MP) GNNs.
  arXiv  Detail & Related papers  (2021-10-07T11:05:23Z)
• Equivariant bifurcation, quadratic equivariants, and symmetry breaking for the standard representation of $S_n$ [15.711517003382484]
  Motivated by questions originating from the study of a class of shallow student-teacher neural networks, methods are developed for the analysis of spurious minima in classes of equivariant dynamics related to neural nets. It is shown that spurious minima do not arise from spontaneous symmetry breaking but rather through a complex deformation of the landscape geometry that can be encoded by a generic $S_n$-equivariant bifurcation. Results on generic bifurcation when there are quadratic equivariants are also proved; this work extends and clarifies results of Ihrig & Golubitsky and Chossat, Lauterback &
  arXiv  Detail & Related papers  (2021-07-06T06:43:06Z)
• UNiTE: Unitary N-body Tensor Equivariant Network with Applications to Quantum Chemistry [33.067344811580604]
  We propose unitary $N$-body tensor equivariant neural network (UNiTE) for general class of symmetric tensors. UNiTE is equivariant with respect to the actions of a unitary group, such as the group of 3D rotations. When applied to quantum chemistry, UNiTE outperforms all state-of-the-art machine learning methods.
  arXiv  Detail & Related papers  (2021-05-31T00:48:18Z)
• Lorentz Group Equivariant Neural Network for Particle Physics [58.56031187968692]
  We present a neural network architecture that is fully equivariant with respect to transformations under the Lorentz group. For classification tasks in particle physics, we demonstrate that such an equivariant architecture leads to drastically simpler models that have relatively few learnable parameters.
  arXiv  Detail & Related papers  (2020-06-08T17:54:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.