2023/12/20 by Rafael Orozco, Philipp Witte, Orozco, Rafael +11
Computer Science · Earth and Planetary Sciences · Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reservoir Engineering and Simulation Methods #Seismic Imaging and Inversion Techniques #Seismology and Earthquake Studies
paper · pdf · doi:10.48550/arxiv.2312.13480
openalex publication_date 2023/12/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
InvertibleNetworks.jl is a Julia package designed for the scalable implementation of normalizing flows, a method for density estimation and sampling in high-dimensional distributions. This package excels in memory efficiency by leveraging the inherent invertibility of normalizing flows, which significantly reduces memory requirements during backpropagation compared to existing normalizing flow packages that rely on automatic differentiation frameworks. InvertibleNetworks.jl has been adapted for diverse applications, including seismic imaging, medical imaging, and CO2 monitoring, demonstrating its effectiveness in learning high-dimensional distributions.