Re-Envisioning Numerical Information Field Theory (NIFTy.re): A Library for Gaussian Processes and Variational Inference

arXiv:2402.16683v1 Announce Type: cross
Abstract: Imaging is the process of transforming noisy, incomplete data into a space that humans can interpret. NIFTy is a Bayesian framework for imaging and has already successfully been applied to many fields in astrophysics. Previous design decisions held the performance and the development of methods in NIFTy back. We present a rewrite of NIFTy, coined NIFTy.re, which reworks the modeling principle, extends the inference strategies, and outsources much of the heavy lifting to JAX. The …

abstract arxiv astro-ph.im astrophysics bayesian cs.lg data decisions design fields framework gaussian processes humans imaging incomplete data inference information library numerical performance process processes space stat.ml theory type