Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition

Abstract

Stein Variational Gradient Descent (SVGD) is an important alternative to the Langevin-type algorithms for sampling from probability distributions of the form $\pi (x)\propto \exp (-V(x))$. In the existing theory of Langevin-type algorithms and SVGD, the potential function $V$ is often assumed to be $L$-smooth. However, this restrictive condition excludes a large class of potential functions such as polynomials of degree greater than $2$. Our paper studies the convergence of the SVGD algorithm for distributions with $(L_0,L_1)$-smooth potentials. This relaxed smoothness assumption was introduced by Zhang et al. [2019a] for the analysis of gradient clipping algorithms. With the help of trajectory-independent auxiliary conditions, we provide a descent lemma establishing that the algorithm decreases the $\mathrm{KL}$ divergence at each iteration and prove a complexity bound for SVGD in the population limit in terms of the Stein Fisher information.

References in corpus (7)

• Stein Variational Gradient Descent With Matrix-Valued Kernels
• On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
• Exponential ergodicity of mirror-Langevin diffusions
• Scalable Thompson Sampling via Optimal Transport
• Analysis of Langevin Monte Carlo from Poincaré to Log-Sobolev
• Stein Variational Gradient Descent: many-particle and long-time asymptotics
• Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets

Cited by in corpus (1)

• Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning