Sequential Monte Carlo Methods for System Identification**This work was supported by the projects Learning of complex dynamical systems (Contract number: 637-2014-466) and Probabilistic modeling of dynamical systems (Contract number: 621-2013-5524), both funded by the Swedish Research Council.

2015/01/01 by Thomas B. Schön, Fredrik Lindsten, Johan Dahlin +4
Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Computer science #Control Systems and Identification #Data mining #Dynamical systems theory #Gaussian Processes and Bayesian Inference #Identification (biology) #Kalman filter #Mathematical optimization #Mathematics #Monte Carlo method #Nonlinear system #Particle filter #Physics #Probabilistic logic #State (computer science) #State space #System identification #Target Tracking and Data Fusion in Sensor Networks #math.OC #stat.CO #stat.ML

paper · pdf · doi:10.1016/j.ifacol.2015.12.224

In proceedings of the 17th IFAC Symposium on System Identification (SYSID). Added cover page

openalex publication_date 2015/01/01 · arxiv created 2016/03/10 · arxiv updated 2016/03/11 · openalex created_date 2022/08/01 · openalex updated_date 2026/06/03

Abstract

One of the key challenges in identifying nonlinear and possibly non-Gaussian state space models (SSMs) is the intractability of estimating the system state. Sequential Monte Carlo (SMC) methods, such as the particle filter (introduced more than two decades ago), provide numerical solutions to the nonlinear state estimation problems arising in SSMs. When combined with additional identification techniques, these algorithms provide solid solutions to the nonlinear system identification problem. We describe two general strategies for creating such combinations and discuss why SMC is a natural tool for implementing these strategies.

Citations

• Branching and interacting particle systems approximations of feynman-kac formulae with applications to non-linear filtering
• Convergence of a stochastic approximation version of the EM algorithm
• Sharp failure rates for the bootstrap particle filter in high dimensions
• A Stable Particle Filter in High-Dimensions
• Nested Sequential Monte Carlo Methods
• Equation of State Calculations by Fast Computing Machines
• Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
• Sequential Monte Carlo smoothing with application to parameter estimation in nonlinear state space models
• The pseudo-marginal approach for efficient Monte Carlo computations
• Novel approach to nonlinear/non-Gaussian Bayesian state estimation
• On the stability of interacting processes with applications to filtering and genetic algorithms
• Sequential Monte Carlo for Graphical Models
• Monte Carlo sampling methods using Markov chains and their applications
• New inference strategies for solving Markov Decision Processes using reversible jump MCMC