Decentralized, Adaptive, Look-Ahead Particle Filtering

The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested sets of variables, the DPF uses a particle filter to sample the first set and then conditions on this sample to generate a set of samples for the second set of variables. The DPF can be understood as a variant of the popular Rao-Blackwellized particle filter (RBPF), where the second step is carried out using Monte Carlo approximations instead of analytical inference. As a result, the range of applications of the DPF is broader than the one for the RBPF. In this paper, we improve the DPF in two ways. First, we derive a Monte Carlo approximation of the optimal proposal distribution and, consequently, design and implement a more efficient look-ahead DPF. Although the decentralized filters were initially designed to capitalize on parallel implementation, we show that the look-ahead DPF can outperform the standard particle filter even on a single machine. Second, we propose the use of bandit algorithms to automatically configure the state space decomposition of the DPF.

[1]  Joaquín Míguez,et al.  Analysis of parallelizable resampling algorithms for particle filtering , 2007, Signal Process..

[2]  D. Lizotte,et al.  An experimental methodology for response surface optimization methods , 2012, J. Glob. Optim..

[3]  Thomas B. Schön,et al.  Marginalized particle filters for mixed linear/nonlinear state-space models , 2005, IEEE Transactions on Signal Processing.

[4]  Freda Kemp,et al.  An Introduction to Sequential Monte Carlo Methods , 2003 .

[5]  Frank Hutter,et al.  Automated configuration of algorithms for solving hard computational problems , 2009 .

[6]  Manuel Davy,et al.  Particle Filtering for Multisensor Data Fusion With Switching Observation Models: Application to Land Vehicle Positioning , 2007, IEEE Transactions on Signal Processing.

[7]  N. D. Freitas.  Rao-Blackwellised particle filtering for fault diagnosis , 2002 .

[8]  Nando de Freitas,et al.  Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks , 2000, UAI.

[9]  Henrik Ohlsson,et al.  Decentralized Particle Filter With Arbitrary State Decomposition , 2011, IEEE Transactions on Signal Processing.

[10]  Arnaud Doucet,et al.  On the Utility of Graphics Cards to Perform Massively Parallel Simulation of Advanced Monte Carlo Methods , 2009, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[11]  Petar M. Djuric,et al.  Resampling algorithms and architectures for distributed particle filters , 2005, IEEE Transactions on Signal Processing.

[12]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[13]  Nando de Freitas,et al.  A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning , 2010, ArXiv.

[14]  Henry A. Kautz,et al.  Learning and inferring transportation routines , 2004, Artif. Intell..

[15]  Alexander J. Smola,et al.  Unified analysis of streaming news , 2011, WWW.

[16]  Nicolò Cesa-Bianchi,et al.  Gambling in a rigged casino: The adversarial multi-armed bandit problem , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[17]  Nando de Freitas,et al.  An Introduction to Sequential Monte Carlo Methods , 2001, Sequential Monte Carlo Methods in Practice.

[18]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[19]  Nando de Freitas,et al.  Diagnosis by a waiter and a Mars explorer , 2004, Proceedings of the IEEE.

[20]  Wei Chu,et al.  A contextual-bandit approach to personalized news article recommendation , 2010, WWW '10.

[21]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[22]  Nando de Freitas,et al.  Toward Practical N2 Monte Carlo: the Marginal Particle Filter , 2005, UAI.

[23]  Arnaud Doucet,et al.  Particle filters for state estimation of jump Markov linear systems , 2001, IEEE Trans. Signal Process..