Poster

Measure Transport with Kernel Stein Discrepancy

Matthew Fisher · Tui Nolan · Matthew Graham · Dennis Prangle · Chris Oates

Keywords: [ Probabilistic Methods ] [ Sampling ]

[ Abstract ]
Thu 15 Apr 7:30 a.m. PDT — 9:30 a.m. PDT
 
Oral presentation: Optimization / Learning Theory / Generalization
Wed 14 Apr 10:30 a.m. PDT — 11:30 a.m. PDT

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.

Chat is not available.