Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory

TL;DR

This paper demonstrates that Transformer models can accurately predict complex scattering amplitude coefficients in planar N=4 Super Yang-Mills theory, showcasing their potential in solving intricate problems in theoretical physics.

Contribution

The study introduces a novel application of Transformers to compute scattering amplitude coefficients, achieving high accuracy in a challenging theoretical physics context.

Findings

Transformers achieved over 98% accuracy in predicting amplitude coefficients.

The approach demonstrates the feasibility of deep learning for exact solutions in high-energy physics.

The method can handle complex mathematical expressions in a language-like format.

Abstract

We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to the theory that describes Higgs boson production at the Large Hadron Collider; its scattering amplitudes are large mathematical expressions containing integer coefficients. In this paper, we apply Transformers to predict these coefficients. The problem can be formulated in a language-like representation amenable to standard cross-entropy training objectives. We design two related experiments and show that the model achieves high accuracy (> 98%) on both tasks. Our work shows that Transformers can be applied successfully to problems in theoretical physics that require exact solutions.