On the geometry of Stein variational gradient descent

Abstract

Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely on iterated steepest descent steps with respect to a reproducing kernel Hilbert space norm. This construction leads to interacting particle systems, the mean-field limit of which is a gradient flow on the space of probability distributions equipped with a certain geometrical structure. We leverage this viewpoint to shed some light on the convergence properties of the algorithm, in particular addressing the problem of choosing a suitable positive definite kernel function. Our analysis leads us to considering certain nondifferentiable kernels with adjusted tails. We demonstrate significant performance gains of these in various numerical experiments.

40 pages, 4 figures

References in corpus (16)

• The Ensemble Kalman Filter for Inverse Problems
• Maximum Mean Discrepancy Gradient Flow
• Message Passing Stein Variational Gradient Descent
• Stein Variational Gradient Descent With Matrix-Valued Kernels
• Understanding and Accelerating Particle-Based Variational Inference
• A stochastic version of Stein Variational Gradient Descent for efficient sampling
• Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
• Stein Variational Gradient Descent as Moment Matching
• Stochastic Gradient MCMC with Repulsive Forces
• Accelerating Langevin Sampling with Birth-death
• Note on Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler by Garbuno-Inigo, Hoffmann, Li and Stuart
• Greedy inference with structure-exploiting lazy maps
• Kernel embedding of maps for sequential Bayesian inference: The variational mapping particle filter
• Particle Optimization in Stochastic Gradient MCMC
• Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference
• Stein Variational Online Changepoint Detection with Applications to Hawkes Processes and Neural Networks

Cited by in corpus (18)

• A Non-Asymptotic Analysis for Stein Variational Gradient Descent
• Repulsive Deep Ensembles are Bayesian
• Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics
• Annealed Stein Variational Gradient Descent
• Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
• On Stein Variational Neural Network Ensembles
• Kernel Stein Discrepancy Descent
• Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition
• Stein Variational Gaussian Processes
• Rough McKean-Vlasov dynamics for robust ensemble Kalman filtering
• The Wasserstein Proximal Gradient Algorithm
• On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
• The equivalence between Stein variational gradient descent and black-box variational inference
• On anisotropic diffusion equations for label propagation
• Relative Entropy Gradient Sampler for Unnormalized Distributions
• Multilevel Stein variational gradient descent with applications to Bayesian inverse problems
• Particle Dynamics for Learning EBMs