Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
Convergence and asymptotic normality of variational Bayesian approximations for exponential family models with missing values
Bo Wang, D. Titterington
Abstract:
We study the properties of variational Bayes approximations for exponential family models with missing values. It is shown that the iterative algorithm for obtaining the variational Bayesian estimator converges locally to the true value with probability 1 as the sample size becomes inde nitely large. Moreover, the variational posterior distribution is proved to be asymptotically normal.
Keywords: null
Pages: 577-584
PS Link:
PDF Link: /papers/04/p577-wang.pdf
BibTex:
@INPROCEEDINGS{Wang04,
AUTHOR = "Bo Wang and D. Titterington",
TITLE = "Convergence and asymptotic normality of variational Bayesian approximations for exponential family models with missing values",
BOOKTITLE = "Proceedings of the Twentieth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-04)",
PUBLISHER = "AUAI Press",
ADDRESS = "Arlington, Virginia",
YEAR = "2004",
PAGES = "577--584"
}


hosted by DSL   •   site info   •   help