p-Kernel Stein Variational Gradient Descent for Data Assimilation and History Matching

Stein Variational Gradient Descent as Gradient Flow

Stein variational gradient descent (SVGD) is a deterministic sampling algorithm that iteratively transports a set of particles to approximate given distributions, based on a gradient-based update that guarantees to optimally decrease the KL divergence within a function space. This paper develops the first theoretical analysis on SVGD. We establish that the empirical measures of the SVGD samples...

Stein Variational Gradient Descent: Theory and Applications

Although optimization can be done very efficiently using gradient-based optimization these days, Bayesian inference or probabilistic sampling has been considered to be much more difficult. Stein variational gradient descent (SVGD) is a new particle-based inference method derived using a functional gradient descent for minimizing KL divergence without explicit parametric assumptions. SVGD can be...

VAE Learning via Stein Variational Gradient Descent

A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make parametric assumptions about the form of the encoder distribution. Performance is further enhanced by integrating the proposed encoder with importance sampling. Excellent performance is demonstrated across multiple unsupe...

Appendix for “VAE Learning via Stein Variational Gradient Descent”

Learning to Draw Samples with Amortized Stein Variational Gradient Descent

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient direction (Liu & Wang, 2016) that maximally decreases the KL divergence with the target distribution. Our method work...