Invertible Neural Networks versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence
This work provides a more efficient and flexible method for analyzing nanostructure parameters for researchers and engineers using GIXRF, which is crucial for applications like computer chip manufacturing.
This paper addresses the reconstruction of posterior parameter distributions in grazing incidence X-ray fluorescence (GIXRF) using invertible neural networks (INNs). The INN method is shown to compete with established Markov Chain Monte Carlo (MCMC) approaches while offering improved efficiency and flexibility.
Grazing incidence X-ray fluorescence is a non-destructive technique for analyzing the geometry and compositional parameters of nanostructures appearing e.g. in computer chips. In this paper, we propose to reconstruct the posterior parameter distribution given a noisy measurement generated by the forward model by an appropriately learned invertible neural network. This network resembles the transport map from a reference distribution to the posterior. We demonstrate by numerical comparisons that our method can compete with established Markov Chain Monte Carlo approaches, while being more efficient and flexible in applications.