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.

InvertibleNetworks.jl 是一个 Julia 软件包，专为实现在高维分布中进行密度估计和抽样的可扩展的可逆流方法而设计。该软件包通过利用可逆流的固有可逆性，在反向传播期间显著降低了内存需求，相较于依赖于自动微分框架的现有的可归一化流软件包，它在内存效率方面表现出色。InvertibleNetworks.jl 已被应用于多个领域，包括地震成像、医学成像和 CO2 监测，证明了其在学习高维分布方面的有效性。