Fast particle smoothing: if I had a million particles

We propose efficient particle smoothing methods for generalized state-spaces models. Particle smoothing is an expensive O(N2 ) algorithm, where N is the number of particles. We overcome this problem by integrating dual tree recursions and fast multipole techniques with forward-backward smoothers, a new generalized two-filter smoother and a maximum a posteriori (MAP) smoother. Our experiments show that these improvements can substantially increase the practicality of particle smoothing.

• Type: Conference
• Year: 2006
• Where: ICML
• Authors: Mike Klaas, Mark Briers, Nando de Freitas, Arnaud Doucet, Simon Maskell, Dustin Lang
• Keywords: Dual Tree Recursions, Efficient Particle Smoothing, Generalized Two-filter Smoother, ICML 2006, Machine Learning