Sequential Monte Carlo Methods for System Identification

TL;DR

This paper discusses how Sequential Monte Carlo methods, especially particle filters, can be combined with other techniques to effectively identify nonlinear and non-Gaussian state space models, addressing the challenge of intractable system state estimation.

Contribution

It introduces two general strategies for integrating SMC methods with system identification techniques, highlighting their natural fit and effectiveness.

Findings

SMC methods provide practical solutions for nonlinear state estimation.

Combining SMC with other techniques enhances system identification capabilities.

The paper discusses strategies for effective integration of SMC in system identification.

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.