Constraining Effective Field Theories with Machine Learning
This work addresses the challenge of improving precision in LHC legacy constraints for particle physics researchers, representing a domain-specific advancement.
The paper tackles the problem of constraining effective field theories at the LHC by developing new analysis techniques that leverage particle physics processes to train neural networks for likelihood ratio estimation, resulting in significantly stronger bounds on dimension-six operators compared to existing methods.
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.