We provide the first convergence guarantee for full black-box variational inference (BBVI), also known as Monte Carlo variational inference. While preliminary investigations worked on simplified versions of BBVI (e.g., bounded domain, bounded support, only optimizing for the scale, and such), our setup does not need any such algorithmic modifications. Our results hold for log-smooth posterior densities with and without strong log-concavity and the location-scale variational family. Also, our analysis reveals that certain algorithm design choices commonly employed in practice, particularly, nonlinear parameterizations of the scale of the variational approximation, can result in suboptimal convergence rates. Fortunately, running BBVI with proximal stochastic gradient descent fixes these limitations, and thus achieves the strongest known convergence rate guarantees. We evaluate this theoretical insight by comparing proximal SGD against other standard implementations of BBVI on large-scale Bayesian inference problems.

翻译：我们首次为全黑箱变分推断（BBVI），亦称蒙特卡洛变分推断，提供了收敛性保证。虽然初步研究着眼于BBVI的简化版本（例如有界域、有界支撑、仅优化尺度参数等），我们的设置无需任何这类算法修改。我们的结果适用于对数光滑后验密度（无论是否具有强对数凹性）以及位置-尺度变分族。此外，我们的分析揭示，实践中某些常见算法设计选择（特别是变分近似尺度的非线性参数化）可能导致次优收敛速率。幸运的是，使用近端随机梯度下降法运行BBVI可弥补这些局限，从而实现已知最强的收敛速率保证。我们通过对比近端SGD与BBVI的其他标准实现在大规模贝叶斯推断问题上的表现，验证了这一理论洞见。