TY - GEN
T1 - Optimal SIR algorithm vs. fully adapted auxiliary particle filter
T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
AU - Desbouvries, François
AU - Petetin, Yohan
AU - Monfrini, Emmanuel
PY - 2011/8/18
Y1 - 2011/8/18
N2 - Particle filters (PF) and auxiliary particle filters (APF) are widely used sequential Monte Carlo (SMC) techniques. In this paper we comparatively analyse the Sampling Importance Resampling (SIR) PF with optimal conditional importance distribution (CID) and the fully adapted APF (FA-APF). Both algorithms share the same Sampling (S), Weighting (W) and Resampling (R) steps, and only differ in the order in which these steps are performed. The order of the operations is not unsignificant: starting at time n - 1 from a common set of particles, we show that one single updated particle at time n will marginally be sampled in both algorithms from the same probability density function (pdf), but as a whole the full set of particles will be conditionally independent if created by the FA-APF algorithm, and dependent if created by the SIR algorithm, which results in support degeneracy.
AB - Particle filters (PF) and auxiliary particle filters (APF) are widely used sequential Monte Carlo (SMC) techniques. In this paper we comparatively analyse the Sampling Importance Resampling (SIR) PF with optimal conditional importance distribution (CID) and the fully adapted APF (FA-APF). Both algorithms share the same Sampling (S), Weighting (W) and Resampling (R) steps, and only differ in the order in which these steps are performed. The order of the operations is not unsignificant: starting at time n - 1 from a common set of particles, we show that one single updated particle at time n will marginally be sampled in both algorithms from the same probability density function (pdf), but as a whole the full set of particles will be conditionally independent if created by the FA-APF algorithm, and dependent if created by the SIR algorithm, which results in support degeneracy.
KW - Auxiliary Particle Filtering
KW - Conditional Independence
KW - Particle Filtering
KW - Sequential Monte Carlo
U2 - 10.1109/ICASSP.2011.5947227
DO - 10.1109/ICASSP.2011.5947227
M3 - Conference contribution
AN - SCOPUS:80051634791
SN - 9781457705397
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 3992
EP - 3995
BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
Y2 - 22 May 2011 through 27 May 2011
ER -