Amortized Bayesian Inference of GISAXS Data with Normalizing Flows

TL;DR

This paper introduces a fast, simulation-based Bayesian inference method using normalizing flows and variational auto-encoders to analyze GISAXS data, significantly reducing computational costs while maintaining accuracy.

Contribution

The authors develop a novel inference framework combining variational auto-encoders and normalizing flows for efficient GISAXS data analysis, outperforming traditional methods like ABC in speed.

Findings

Reduces inference time by orders of magnitude

Produces consistent results with ABC

Effective on experimental GISAXS data

Abstract

Grazing-Incidence Small-Angle X-ray Scattering (GISAXS) is a modern imaging technique used in material research to study nanoscale materials. Reconstruction of the parameters of an imaged object imposes an ill-posed inverse problem that is further complicated when only an in-plane GISAXS signal is available. Traditionally used inference algorithms such as Approximate Bayesian Computation (ABC) rely on computationally expensive scattering simulation software, rendering analysis highly time-consuming. We propose a simulation-based framework that combines variational auto-encoders and normalizing flows to estimate the posterior distribution of object parameters given its GISAXS data. We apply the inference pipeline to experimental data and demonstrate that our method reduces the inference cost by orders of magnitude while producing consistent results with ABC.