LUCI is an general-purpose spectral line-fitting pipeline which natively integrates machine learning algorithms to initialize fit functions. LUCI currently uses point-estimates obtained from a convolutional neural network (CNN) to inform optimization algorithms; this methodology has shown great promise by reducing computation time and reducing the chance of falling into a local minimum using convex optimization methods. In this update to LUCI, we expand upon the CNN developed in Rhea et al. 2020 so that it outputs Gaussian posterior distributions of the fit parameters of interest (the velocity and broadening) rather than simple point-estimates. Moreover, these posteriors are then used to inform the priors in a Bayesian inference scheme, either emcee or dynesty. The code is publicly available at https://github.com/crhea93/LUCI.
@article{arxiv.2111.12755,
title = {Updates to LUCI: A New Fitting Paradigm Using Mixture Density Networks},
author = {Carter L. Rhea and Julie Hlavacek-Larrondo and Laurie Rousseau-Nepton and Simon Prunet},
journal= {arXiv preprint arXiv:2111.12755},
year = {2021}
}
Comments
Submitted to RNAAS. Code can be found at https://github.com/crhea93/LUCI