Amplitude Surrogates for Multi-Jet Processes

TL;DR

This paper presents a hybrid neural network architecture that predicts multi-jet amplitudes at the LHC by combining theoretical factorization with data-driven corrections, achieving fast and accurate results.

Contribution

It introduces a novel neural network design leveraging the Catani-Seymour scheme, enabling scalable and precise amplitude predictions with integrated accuracy estimation.

Findings

Speed-up factors of up to 20 in event generation

Maintains percent-level accuracy in observables

Efficiently estimates prediction uncertainties

Abstract

Accurate and efficient amplitude predictions are essential for precision studies of multi-jet processes at the LHC. We introduce a novel neural network architecture that predicts multi-jet amplitudes by leveraging the Catani-Seymour factorization scheme and related lower-jet amplitudes, requiring the network to learn only a correction factor. This hybrid approach combines theoretical factorization with a data-driven ansatz, enabling fast and scalable amplitude predictions. Our networks also estimate the accuracy of each prediction, allowing us to selectively use results that meet a predefined accuracy threshold. In the context of leading-order event generation, this approach achieves speed-up factors of up to 20 while maintaining all observables at the percent-level accuracy.