Particle Smoothing for Hidden Diffusion Processes: Adaptive Path Integral Smoother

DOI10.1109/TSP.2017.2686340MaRDI QIDQ4621721zbMATH OpenOpenAlexFDO

Authors H. C. Ruiz, Hilbert J. Kappen

Publication date 8 February 2019

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1605.00278

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Particle smoothing methods are used for inference of stochastic processes based on noisy observations. Typically, the estimation of the marginal posterior distribution given all observations is cumbersome and computational intensive. In this paper, we propose a simple algorithm based on path integral control theory to estimate the smoothing distribution of continuous-time diffusion processes with partial observations. In particular, we use an adaptive importance sampling method to improve the effective sampling size of the posterior over processes given the observations and the reliability of the estimation of the marginals. This is achieved by estimating a feedback controller to sample efficiently from the joint smoothing distributions. We compare the results with estimations obtained from the standard Forward Filter/Backward Simulator for two diffusion processes of different complexity. We show that the proposed method gives more reliable estimations than the standard FFBSi when the smoothing distribution is poorly represented by the filter distribution.

Cited in

(12)

• An iterative Bayesian filtering framework for fast and automated calibration of DEM models
• Solving quantum stochastic LQR optimal control problem in Fock space and its application in finance
• Controlled sequential Monte Carlo
• Particle Smoothing in Continuous Time: A Fast Approach via Density Estimation
• Smoothing with couplings of conditional particle filters
• An optimal control derivation of nonlinear smoothing equations
• Adaptive smoothing for path integral control
• Data assimilation: the Schrödinger perspective
• Learning effective state-feedback controllers through efficient multilevel importance samplers
• Adaptive path-integral autoencoder: representation learning and planning for dynamical systems
• A multilevel approach for stochastic nonlinear optimal control
• An optimal control approach to particle filtering

This page was built for publication: Particle Smoothing for Hidden Diffusion Processes: Adaptive Path Integral Smoother

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4621721)