Variational Autoencoder with Normalizing flow for X-ray spectral fitting

TL;DR

This paper presents a novel probabilistic model combining variational autoencoders and normalizing flows to efficiently and accurately fit X-ray spectra from black hole binaries, surpassing traditional methods in speed and precision.

Contribution

The authors introduce a new neural network-based spectral fitting method that models physical parameters probabilistically, achieving faster and more accurate results than existing techniques.

Findings

Significant improvement in spectral reconstruction accuracy.

Three orders of magnitude faster than traditional MCMC methods.

Effective modeling of physical parameter distributions.

Abstract

Black hole X-ray binaries (BHBs) can be studied with spectral fitting to provide physical constraints on accretion in extreme gravitational environments. Traditional methods of spectral fitting such as Markov Chain Monte Carlo (MCMC) face limitations due to computational times. We introduce a probabilistic model, utilizing a variational autoencoder with a normalizing flow, trained to adopt a physical latent space. This neural network produces predictions for spectral-model parameters as well as their full probability distributions. Our implementations result in a significant improvement in spectral reconstructions over a previous deterministic model while performing three orders of magnitude faster than traditional methods.