Lack of Consistency of Mean Field and Variational Bayes Approximations for State Space Models
Lack of Consistency of Mean Field and Variational Bayes Approximations for State Space Models
Bo Wang,D. Titterington
2004 · DOI: 10.1007/s11063-004-2024-6
Neural Processing Letters · 59 Citations
TLDR
It is proved that the mean field approximation is asymptotically consistent when the variances of the noise variables in the system are sufficiently small, but neither themean field estimator nor the variational Bayes estimator is always asymptonically consistent as the ‘sample size’ becomes large.
