Variational inference is an increasingly popular method in statistics and machine learning for approximating probability distributions. We developed LINFA (Library for Inference with Normalizing Flow and Annealing), a Python library for variational inference to accommodate computationally expensive models and difficult-to-sample distributions with dependent parameters. We discuss the theoretical background, capabilities, and performance of LINFA in various benchmarks. LINFA is publicly available on GitHub at https://github.com/desResLab/LINFA.

翻译：变分推断是统计学与机器学习中日益流行的概率分布近似方法。我们开发了LINFA（基于归一化流与退火的推断库），这是一个用于变分推断的Python库，旨在适配计算成本高昂的模型及参数依赖导致的难以采样的分布。本文讨论了LINFA的理论背景、功能特性以及在多个基准测试中的性能表现。LINFA已在GitHub上开源，仓库地址为https://github.com/desResLab/LINFA。