PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics
This work addresses the need for more efficient and physics-principled machine learning tools in particle physics, offering a novel architecture that improves performance while reducing complexity, though it is incremental in applying symmetry principles to specific tasks.
The authors tackled the problem of inefficient and non-physics-aware machine learning models in particle physics by introducing PELICAN, a permutation-equivariant and Lorentz-invariant/covariant network architecture that reduces input dimensions and respects underlying symmetries, achieving state-of-the-art performance in top quark tagging with lower model complexity and demonstrating applicability to 4-momentum regression.
Many current approaches to machine learning in particle physics use generic architectures that require large numbers of parameters and disregard underlying physics principles, limiting their applicability as scientific modeling tools. In this work, we present a machine learning architecture that uses a set of inputs maximally reduced with respect to the full 6-dimensional Lorentz symmetry, and is fully permutation-equivariant throughout. We study the application of this network architecture to the standard task of top quark tagging and show that the resulting network outperforms all existing competitors despite much lower model complexity. In addition, we present a Lorentz-covariant variant of the same network applied to a 4-momentum regression task.