Repository: Freie Universit├Ąt Berlin, Math Department

Kernel Sequential Monte Carlo

Schuster, I. and Strathmann, H. and Paige, B. and Sejdinovic, Dino (2015) Kernel Sequential Monte Carlo. SFB 1114 Preprint in arXiv:1510.03105 . (Submitted)

[img]
Preview
PDF
2MB

Official URL: https://arxiv.org/abs/1510.03105

Abstract

We propose kernel sequential Monte Carlo (KSMC), a framework for sampling from static target densities. KSMC is a family of sequential Monte Carlo algorithms that are based on building emulator models of the current particle system in a reproducing kernel Hilbert space. We here focus on modelling nonlinear covariance structure and gradients of the target. The emulator's geometry is adaptively updated and subsequently used to inform local proposals. Unlike in adaptive Markov chain Monte Carlo, continuous adaptation does not compromise convergence of the sampler. KSMC combines the strengths of sequental Monte Carlo and kernel methods: superior performance for multimodal targets and the ability to estimate model evidence as compared to Markov chain Monte Carlo, and the emulator's ability to represent targets that exhibit high degrees of nonlinearity. As KSMC does not require access to target gradients, it is particularly applicable on targets whose gradients are unknown or prohibitively expensive. We describe necessary tuning details and demonstrate the benefits of the the proposed methodology on a series of challenging synthetic and real-world examples.

Item Type:Article
Additional Information:To appear in the book "European Conference on Machine Learning and Principles of Knowledge Discovery in Databases"
Subjects:Mathematical and Computer Sciences > Mathematics > Applied Mathematics
ID Code:2164
Deposited By: Silvia Hoemke
Deposited On:13 Dec 2017 09:59
Last Modified:26 Feb 2018 12:33

Repository Staff Only: item control page