DeepXS: Fast approximation of MSSM electroweak cross sections at NLO

TL;DR

DeepXS employs deep learning to rapidly predict MSSM electroweak cross sections at NLO, achieving high accuracy and vastly faster inference times compared to traditional Monte Carlo methods, facilitating efficient SUSY phenomenology studies.

Contribution

This work introduces a deep learning approach for fast, accurate approximation of complex particle physics cross sections at NLO in the MSSM-19 parameter space.

Findings

Achieves mean absolute percentage errors below 0.5%.

Reduces inference time by a factor of 10^7 compared to Monte Carlo methods.

Demonstrates applicability to key SUSY particle production processes.

Abstract

We present a deep learning solution to the prediction of particle production cross sections over a complicated, high-dimensional parameter space. We demonstrate the applicability by providing state-of-the-art predictions for the production of charginos and neutralinos at the Large Hadron Collider (LHC) at the next-to-leading order in the phenomenological MSSM-19 and explicitly demonstrate the performance for $pp\to\tilde{\chi}^+_1\tilde{\chi}^-_1,$ $\tilde{\chi}^0_2\tilde{\chi}^0_2$ and $\tilde{\chi}^0_2\tilde{\chi}^\pm_1$ as a proof of concept which will be extended to all SUSY electroweak pairs. We obtain errors that are lower than the uncertainty from scale and parton distribution functions with mean absolute percentage errors of well below $0.5\,\%$ allowing a safe inference at the next-to-leading order with inference times that improve the Monte Carlo integration procedures that have been available so far by a factor of $\mathcal{O}(10^7)$ from $\mathcal{O}(\rm{min})$ to $\mathcal{O}(\mu\rm{s})$ per evaluation.