Filtering with state-observation examples via kernel Monte Carlo filter

DOI10.1162/NECO_A_00806zbMATH Open1418.62361arXiv1312.4664WikidataQ40225681 ScholiaQ40225681MaRDI QIDQ5380397FDOQ5380397

Yu Nishiyama, Motonobu Kanagawa, Kenji Fukumizu, Arthur Gretton

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Abstract: This paper addresses the problem of filtering with a state-space model. Standard approaches for filtering assume that a probabilistic model for observations (i.e. the observation model) is given explicitly or at least parametrically. We consider a setting where this assumption is not satisfied; we assume that the knowledge of the observation model is only provided by examples of state-observation pairs. This setting is important and appears when state variables are defined as quantities that are very different from the observations. We propose Kernel Monte Carlo Filter, a novel filtering method that is focused on this setting. Our approach is based on the framework of kernel mean embeddings, which enables nonparametric posterior inference using the state-observation examples. The proposed method represents state distributions as weighted samples, propagates these samples by sampling, estimates the state posteriors by Kernel Bayes' Rule, and resamples by Kernel Herding. In particular, the sampling and resampling procedures are novel in being expressed using kernel mean embeddings, so we theoretically analyze their behaviors. We reveal the following properties, which are similar to those of corresponding procedures in particle methods: (1) the performance of sampling can degrade if the effective sample size of a weighted sample is small; (2) resampling improves the sampling performance by increasing the effective sample size. We first demonstrate these theoretical findings by synthetic experiments. Then we show the effectiveness of the proposed filter by artificial and real data experiments, which include vision-based mobile robot localization.

Full work available at URL: https://arxiv.org/abs/1312.4664

Recommendations

• The kernel Kalman rule. Efficient nonparametric inference by recursive least-squares and subspace projections
• Sequential Monte Carlo with kernel embedded mappings: the mapping particle filter
• Adaptive kernels in approximate filtering of state-space models
• Robust filtering
• The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Nongaussian Observation Models

zbMATH Keywords

state-space modelfiltering

Mathematics Subject Classification ID

Directional data; spatial statistics (62H11) Inference from stochastic processes and prediction (62M20) Applications of statistics to physics (62P35)

Cites Work

• Sequential Monte Carlo Methods in Practice
• 10.1162/15324430260185619
• Title not available (Why is that?)
• Theory of Reproducing Kernels
• Consistent nonparametric regression. Discussion
• Hilbert space embeddings and metrics on probability measures
• Title not available (Why is that?)
• 10.1162/153244303768966085
• Title not available (Why is that?)
• Support Vector Machines
• A Hilbert Space Embedding for Distributions
• Title not available (Why is that?)
• Monte Carlo strategies in scientific computing
• Kernel methods in machine learning
• Title not available (Why is that?)
• Filtering via approximate Bayesian computation
• Time series analysis by state space methods.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• New analysis and results for the Frank-Wolfe method
• Asymptotic behavior of the eigenvalues of certain integral equations. II
• Asymptotic Behavior of the Eigenvalues of Certain Integral Equations
• Optimal regression rates for SVMs using Gaussian kernels
• Title not available (Why is that?)

Cited In (3)

• Convergence analysis of deterministic kernel-based quadrature rules in misspecified settings
• Title not available (Why is that?)
• Model-based kernel sum rule: kernel Bayesian inference with probabilistic models

This page was built for publication: Filtering with state-observation examples via kernel Monte Carlo filter

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380397)