ELSA -- Enhanced latent spaces for improved collider simulations

TL;DR

This paper introduces novel machine learning techniques to enhance collider simulation accuracy, employing latent space refinement and reweighting methods to achieve sub-percent precision in complex particle physics scenarios.

Contribution

It presents new approaches for improving collider simulations using latent space refinement and reweighting, including a general method for massive particles at hadron colliders.

Findings

Modified simulations reach sub-percent precision.

Latent space refinement improves simulation accuracy.

New pre-processing method for massive particles.

Abstract

Simulations play a key role for inference in collider physics. We explore various approaches for enhancing the precision of simulations using machine learning, including interventions at the end of the simulation chain (reweighting), at the beginning of the simulation chain (pre-processing), and connections between the end and beginning (latent space refinement). To clearly illustrate our approaches, we use W+jets matrix element surrogate simulations based on normalizing flows as a prototypical example. First, weights in the data space are derived using machine learning classifiers. Then, we pull back the data-space weights to the latent space to produce unweighted examples and employ the Latent Space Refinement (LASER) protocol using Hamiltonian Monte Carlo. An alternative approach is an augmented normalizing flow, which allows for different dimensions in the latent and target spaces. These methods are studied for various pre-processing strategies, including a new and general method for massive particles at hadron colliders that is a tweak on the widely-used RAMBO-on-diet mapping. We find that modified simulations can achieve sub-percent precision across a wide range of phase space.