Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
Bounds on the Bethe Free Energy for Gaussian Networks
Botond Cseke, Tom Heskes
Abstract:
We address the problem of computing approximate marginals in Gaussian probabilistic models by using mean field and fractional Bethe approximations. As an extension of Welling and Teh (2001), we define the Gaussian fractional Bethe free energy in terms of the moment parameters of the approximate marginals and derive an upper and lower bound for it. We give necessary conditions for the Gaussian fractional Bethe free energies to be bounded from below. It turns out that the bounding condition is the same as the pairwise normalizability condition derived by Malioutov et al. (2006) as a sufficient condition for the convergence of the message passing algorithm. By giving a counterexample, we disprove the conjecture in Welling and Teh (2001): even when the Bethe free energy is not bounded from below, it can possess a local minimum to which the minimization algorithms can converge.
Keywords: null
Pages: 97-104
PS Link:
PDF Link: /papers/08/p97-cseke.pdf
BibTex:
@INPROCEEDINGS{Cseke08,
AUTHOR = "Botond Cseke and Tom Heskes",
TITLE = "Bounds on the Bethe Free Energy for Gaussian Networks",
BOOKTITLE = "Proceedings of the Twenty-Fourth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-08)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "2008",
PAGES = "97--104"
}


hosted by DSL   •   site info   •   help