Scaffolding Simulations with Deep Learning for High-dimensional Deconvolution

TL;DR

This paper introduces OmniFold, a deep learning-based method for high-dimensional deconvolution that removes detector distortions and noise from simulation data, enabling improved scientific inference without explicit data densities.

Contribution

The paper presents OmniFold, a novel deep learning approach for high-dimensional, simulation-based deconvolution that generalizes Richardson-Lucy and handles noise and acceptance effects.

Findings

OmniFold effectively removes detector distortions.

The method accounts for noise and acceptance effects.

It enables accurate downstream scientific inference.

Abstract

A common setting for scientific inference is the ability to sample from a high-fidelity forward model (simulation) without having an explicit probability density of the data. We propose a simulation-based maximum likelihood deconvolution approach in this setting called OmniFold. Deep learning enables this approach to be naturally unbinned and (variable-, and) high-dimensional. In contrast to model parameter estimation, the goal of deconvolution is to remove detector distortions in order to enable a variety of down-stream inference tasks. Our approach is the deep learning generalization of the common Richardson-Lucy approach that is also called Iterative Bayesian Unfolding in particle physics. We show how OmniFold can not only remove detector distortions, but it can also account for noise processes and acceptance effects.