Constraining Effective Field Theories with Machine Learning.

By J. Brehmer, Kyle Cranmer, Gilles Louppe, Juan Pavez. 2018

172 citations recorded by the source corpus.

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.

Subfields: Nuclear and High Energy Physics, AI for Physical Sciences

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Nuclear and High Energy Physics

In AI for Physical Sciences

Citations in the corpus

Normalizing Flows for Probabilistic Modeling and Inference (2019, methodology): “, 2018), high-energy physics (Brehmer et al., 2018), and computational neuroscience”
Likelihood-free inference with emulator networks (2018, background): “Approximate Bayesian Computation (ABC) aims to close this gap by providing Bayesian inference algorithms that can be used with simulator models without requiring explicit likelihoods [3, 4, 5, 6, 7].”
Likelihood-free inference with an improved cross-entropy estimator (2018, methodology): “[24–26] coined the term “mining gold” for the process of extracting the joint likelihood ratio and joint score from the simulator – while the augmented data require some effort to extract, they are extremely valuable.”
Energy flow networks: deep sets for particle jets (2018, unknown): “Additional tasks include the removal of pileup [30], model-independent new physics searches [31–36], constraining effective field theories [37–39], probabilistic and generative modeling of physics processes [40–44], and enhancing existing physics analyses [45–53].”
Mining for Dark Matter Substructure: Inferring Subhalo Population Properties from Strong Lenses with Machine Learning (2019, methodology): “In this paper, we follow this approach and apply a particularly powerful technique for simulation-based inference introduced in Brehmer et al. (2018a, 2018b, 2018c) and Stoye et al. (2018) to the problem of extracting high-level substructure properties from an ensemble of galaxy–galaxy…”
Fast likelihood-free cosmology with neural density estimators and active learning (2019, methodology): “As a third approach, the score-function may be regressed directly from simulations in a likelihood-free manner using neural networks (Brehmer et al. 2018a,b,c).”