Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion

TL;DR

This paper introduces a novel variational latent diffusion model capable of full-event unfolding in high-dimensional, variable-length feature spaces, improving detector response correction in collider data analysis.

Contribution

It presents a new modification to the VLD model enabling unfolding of variable-dimensional data, addressing limitations of previous fixed-observable approaches.

Findings

Effective in semi-leptonic top quark pair production data

Handles high- and variable-dimensional feature spaces

Improves accuracy of detector response correction

Abstract

The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider.