Variational inference is a fast and scalable alternative to Markov chain Monte Carlo and has been widely applied to posterior inference tasks in statistics and machine learning. A traditional approach for implementing mean-field variational inference (MFVI) is coordinate ascent variational inference (CAVI), which relies crucially on parametric assumptions on complete conditionals. We introduce a novel particle-based algorithm for MFVI, named PArticle VI (PAVI), for nonparametric mean-field approximation. We obtain non-asymptotic error bounds for our algorithm. To our knowledge, this is the first end-to-end guarantee for particle-based MFVI.

翻译：变分推断是马尔可夫链蒙特卡罗方法的一种快速且可扩展的替代方案，已广泛应用于统计学和机器学习中的后验推断任务。实现平均场变分推断（MFVI）的传统方法是坐标上升变分推断（CAVI），该方法关键依赖于对完全条件分布的参数化假设。我们提出了一种新颖的基于粒子的算法，用于非参数平均场近似，命名为粒子变分推断（PAVI）。我们为该算法获得了非渐近误差界。据我们所知，这是首个基于粒子的MFVI的端到端保证。