Differentiable Matrix Elements with MadJax

Abstract

MadJax is a tool for generating and evaluating differentiable matrix elements of high energy scattering processes. As such, it is a step towards a differentiable programming paradigm in high energy physics that facilitates the incorporation of high energy physics domain knowledge, encoded in simulation software, into gradient based learning and optimization pipelines. MadJax comprises two components: (a) a plugin to the general purpose matrix element generator MadGraph that integrates matrix element and phase space sampling code with the JAX differentiable programming framework, and (b) a standalone wrapping API for accessing the matrix element code and its gradients, which are computed with automatic differentiation. The MadJax implementation and example applications of simulation based inference and normalizing flow based matrix element modeling, with capabilities enabled uniquely with differentiable matrix elements, are presented.

arXiv comment6 pages, Proceedings of the 20th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2021)

References in corpus (8)

• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The frontier of simulation-based inference
• TorchMD: A deep learning framework for molecular simulations
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Mining gold from implicit models to improve likelihood-free inference
• ALOHA: Automatic Libraries Of Helicity Amplitudes for Feynman diagram computations
• Exploring phase space with Neural Importance Sampling
• PDFFlow: parton distribution functions on GPU

Cited by in corpus (7)

• Machine Learning and LHC Event Generation
• Event Generators for High-Energy Physics Experiments
• MadNIS -- Neural Multi-Channel Importance Sampling
• Differentiable MadNIS-Lite
• LINX: A Fast, Differentiable, and Extensible Big Bang Nucleosynthesis Package
• Constraining the Higgs Potential with Neural Simulation-based Inference for Di-Higgs Production
• Flow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics