ON THE CONVERGENCE OF COORDINATE ASCENT VARIATIONAL INFERENCE

• 成果类型: Article
• 署名作者: Bhattacharya, Anirban; Pati, Debdeep; Yang, Yun
• 署名单位: Texas A&M University System; Texas A&M University College Station; University of Wisconsin System; University of Wisconsin Madison; University System of Maryland; University of Maryland College Park
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/24-AOS2481
• 发表日期: 2025
• 页码: 929-962
• 关键词: Asymptotic Normality; approximation; guarantees; algorithm

摘要

As a computational alternative to Markov chain Monte Carlo approaches, variational inference (VI) is becoming more and more popular for approximating intractable posterior distributions in large-scale Bayesian models due to its comparable efficacy and superior efficiency. Several recent works provide theoretical justifications of VI by proving its statistical optimality for parameter estimation under various settings; meanwhile, formal analysis on the algorithmic convergence aspects of VI is still largely lacking. In this paper, we consider the common coordinate ascent variational inference (CAVI) algorithm for implementing the mean-field (MF) VI towards optimizing a Kullback-Leibler divergence objective functional over the space of all factorized distributions. Focusing on the two-block case, we analyze the convergence of CAVI by leveraging the extensive toolbox from functional analysis and optimization. We provide general conditions for certifying global or local exponential convergence of CAVI. Specifically, a new notion of generalized correlation for characterizing the interaction between the constituting blocks in influencing the VI objective functional is introduced, which according to the theory, quantifies the algorithmic contraction rate of two-block CAVI. As illustrations, we apply the theory to a number of examples, and derive explicit problem-dependent upper bounds on the algorithmic contraction rate.