A Lorentz-Equivariant Transformer for All of the LHC
This addresses the need for efficient and accurate models in high-energy physics, offering a novel architecture that is not incremental but provides broad improvements for LHC applications.
The paper tackled machine learning tasks at the Large Hadron Collider by introducing L-GATr, a Lorentz-equivariant transformer, and achieved state-of-the-art performance with significant improvements in amplitude regression, jet classification, and generative modeling.
We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and is equivariant under Lorentz transformations. The underlying architecture is a versatile and scalable transformer, which is able to break symmetries if needed. We demonstrate the power of L-GATr for amplitude regression and jet classification, and then benchmark it as the first Lorentz-equivariant generative network. For all three LHC tasks, we find significant improvements over previous architectures.