Ever wished to study extra about particle filters, sequential Monte Carlo, state-space/hidden Markov fashions, PMCMC (particle MCMC) , SMC samplers, and associated matters?
In that case, you would possibly wish to examine the next guide from Omiros Papaspiliopoulos and I, which has simply been launched by Springer:
and which can be ordered from their web-site, or out of your favorite guide retailer.
The purpose of the guide is to cowl the numerous aspects of SMC: the algorithms, their sensible makes use of in several areas, the underlying principle, how they might be applied in apply, and so forth. Every chapter incorporates a “Python nook” which discusses the sensible implementation of the lined strategies in Python, a set of workouts, and bibliographical notes. Talking of chapters, right here is the desk of contents:
- Introduction
- Introduction to state-space fashions
- Past state-space fashions
- Introduction to Markov processes
- Feynman-Kac fashions: definition, properties and recursions
- Finite state-spaces and hidden Markov fashions
- Linear-Gaussian state-space fashions
- Significance sampling
- Significance resampling
- Particle filtering
- Convergence and stability of particle filters
- Particle smoothing
- Sequential quasi-Monte Carlo
- Most probability estimation of state-space fashions
- Markov chain Monte Carlo
- Bayesian estimation of state-space fashions and particle MCMC
- SMC samplers
- SMC^2, sequential inference in state-space fashions
- Superior matters and open issues
And right here is one fancy plot taken from the guide. (For some clarification, you’ll have to learn it!)
An enormous because of all of the colleagues who took the time to learn draft variations and ship suggestions (see the introduction for an inventory of names). Additionally, don’t write books, of us. Severely, it takes WAY an excessive amount of time…
