Measure Transport with Kernel Stein Discrepancy

Abstract

Measure transport underpins several recent algorithms for posterior approximation in the Bayesian context, wherein a transport map is sought to minimise the Kullback--Leibler divergence (KLD) from the posterior to the approximation. The KLD is a strong mode of convergence, requiring absolute continuity of measures and placing restrictions on which transport maps can be permitted. Here we propose to minimise a kernel Stein discrepancy (KSD) instead, requiring only that the set of transport maps is dense in an $L^2$ sense and demonstrating how this condition can be validated. The consistency of the associated posterior approximation is established and empirical results suggest that KSD is competitive and more flexible alternative to KLD for measure transport.

References in corpus (7)

• NICE: Non-linear Independent Components Estimation
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• MADE: Masked Autoencoder for Distribution Estimation
• Training generative neural networks via Maximum Mean Discrepancy optimization
• Optimizing The Integrator Step Size for Hamiltonian Monte Carlo
• MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
• Variational Mixture of Normalizing Flows

Cited by in corpus (1)

• Kernel Stein Discrepancy Descent