提出新型粒子算法，实现非参数化均场变分推断的理论保证。
A Particle Algorithm for Mean-Field Variational Inference
- 用粒子方法替代传统参数假设，实现非参数均场近似。
- 首次给出粒子型均场推断的非渐近误差界。
- 适合需要理论保障的复杂后验推断任务。
变分推断是马尔可夫链蒙特卡洛的快速可扩展替代方法，广泛应用于统计与机器学习中的后验推断。传统均场变分推断（MFVI）常采用坐标上升变分推断（CAVI），依赖于完整条件分布的参数假设。本文提出一种基于粒子的新算法PArticle VI（PAVI），用于非参数均场近似，并给出了该算法的非渐近误差界。据我们所知，这是首个针对粒子型均场推断的端到端理论保证。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。