Advancing Tools for Simulation-Based Inference

TL;DR

This paper enhances simulation-based inference tools for particle physics by integrating physics structures, improving algorithms, and demonstrating increased stability and control in LHC di-boson production analysis.

Contribution

It introduces a new smearing algorithm, methods for uncertainty approximation, and the use of equivariant networks to improve likelihood estimation in particle physics.

Findings

Improved numerical control and stability in LHC di-boson analysis

Effective incorporation of physics structures into likelihood estimation

Enhanced inference accuracy with new algorithms and network architectures

Abstract

We study the benefit of modern simulation-based inference to constrain particle interactions at the LHC. We explore ways to incorporate known physics structures into likelihood estimation, specifically morphing-aware estimation and derivative learning. Technically, we introduce a new and more efficient smearing algorithm, illustrate how uncertainties can be approximated through repulsive ensembles, and show how equivariant networks can improve likelihood estimation. After illustrating these aspects for a toy model, we target di-boson production at the LHC and find that our improvements significantly increase numerical control and stability.