Constraining Effective Field Theories with Machine Learning

TL;DR

This paper introduces machine learning techniques to efficiently constrain effective field theories at the LHC, enabling stronger bounds on operators and faster evaluations without approximations.

Contribution

It develops neural network-based likelihood ratio estimators that leverage particle physics structure, improving constraint strength and computational speed over existing methods.

Findings

Stronger bounds on dimension-six operators achieved

Methods scale well with many observables and parameters

Likelihood ratio estimators evaluated in microseconds

Abstract

We present powerful new analysis techniques to constrain effective field theories at the LHC. By leveraging the structure of particle physics processes, we extract extra information from Monte-Carlo simulations, which can be used to train neural network models that estimate the likelihood ratio. These methods scale well to processes with many observables and theory parameters, do not require any approximations of the parton shower or detector response, and can be evaluated in microseconds. We show that they allow us to put significantly stronger bounds on dimension-six operators than existing methods, demonstrating their potential to improve the precision of the LHC legacy constraints.