Rao-blackwellized sampling for batch and recursive Bayesian inference of piecewise affine models

DOI10.1016/j.automatica.2020.109002zbMath1442.93039OpenAlexW3018134872MaRDI QIDQ2184548

Alessio Benavoli, Dario Piga, Alberto Bemporad

Publication date: 29 May 2020

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2020.109002

zbMATH Keywords

recursive identificationMarkov chain Monte CarloBayesian inferenceparticle filterspiecewise-affine regression

Mathematics Subject Classification ID

Bayesian inference (62F15) Applications of statistics in engineering and industry; control charts (62P30) Nonlinear systems in control theory (93C10) Stochastic systems in control theory (general) (93E03)

Related Items (5)

Model structure selection for switched NARX system identification: a randomized approach ⋮ Optimistic optimization for continuous nonconvex piecewise affine functions ⋮ A randomized method for the identification of switched NARX systems ⋮ Estimation of jump Box-Jenkins models ⋮ Nonlinear desirability as a linear classification problem

Uses Software

• Hybrid Stable Spline Toolbox
• PRMLT

Cites Work

• Unnamed Item
• A new kernel-based approach to hybrid system identification
• Identification of switched linear systems via sparse optimization
• A recursive identification algorithm for switched linear/affine models
• On the complexity of piecewise affine system identification
• Control of systems integrating logic, dynamics, and constraints
• An introduction to MCMC for machine learning
• Identification of piecewise affine systems via mixed-integer programming.
• Fitting jump models
• A clustering technique for the identification of piecewise affine systems
• An SDP approach for \(\ell_0\)-minimization: application to ARX model segmentation
• Piecewise affine regression via recursive multiple least squares and multicategory discrimination
• Identification of switched linear regression models using sum-of-norms regularization
• Observability and controllability of piecewise affine and hybrid systems
• Rao-Blackwellisation of sampling schemes
• Hinging hyperplanes for regression, classification, and function approximation
• A Bayesian approach to identification of hybrid systems
• A bounded-error approach to piecewise affine system identification
• Equivalence of hybrid dynamical models

This page was built for publication: Rao-blackwellized sampling for batch and recursive Bayesian inference of piecewise affine models