Convexifying the Bethe Free Energy
نویسندگان
چکیده
The introduction of loopy belief propagation (LBP) revitalized the application of graphical models in many domains. Many recent works present improvements on the basic LBP algorithm in an attempt to overcome convergence and local optima problems. Notable among these are convexified free energy approximations that lead to inference procedures with provable convergence and quality properties. However, empirically LBP still outperforms most of its convex variants in a variety of settings, as we also demonstrate here. Motivated by this fact we seek convexified free energies that directly approximate the Bethe free energy. We show that the proposed approximations compare favorably with state-of-the art convex free energy approximations.
منابع مشابه
Bethe Free Energy and Locally Consistent Marginals Lecturer : Andrea Montanari Scribe : Krishnamurthy Iyer 1 Bethe Free Energy
. Note that there are three terms in the expression, one for each edge, one for each factor node, and one for each variable node in the factor graph. The following claim justifies the study of Bethe free energy. Claim 1. For any factor graph, the stationary points of the Bethe free energy correspond to the fixed points of the Belief Propagation algorithm and vice versa. That is, ∂GB ∂ν = 0 if a...
متن کاملThe Bethe Permanent of a Non - Negative Matrix ∗ Pascal
It has recently been observed that the permanent of a non-negative matrix, i.e., of a matrix containing only nonnegative real entries, can very well be approximated by solving a certain Bethe free energy minimization problem with the help of the sum-product algorithm. We call the resulting approximation of the permanent the Bethe permanent. In this paper we give reasons why this approach to app...
متن کاملAn approximate analytical solution of the Bethe equation for charged particles in the range of radiotherapy energy
Charged particles such as protons and carbon ions are an increasing tool in radiation therapy. However, unresolved physical problems prevent optimal performance, including estimating the deposited dose in non-homogeneous tissue, is an essential aspect of optimizing treatment. The Monte Carlo (MC) method can be used to estimate the amount of radiation, but, this powerful computing operation is v...
متن کاملGraph Zeta Function in the Bethe Free Energy and Loopy Belief Propagation
We propose a new approach to the analysis of Loopy Belief Propagation (LBP) byestablishing a formula that connects the Hessian of the Bethe free energy with theedge zeta function. The formula has a number of theoretical implications on LBP.It is applied to give a sufficient condition that the Hessian of the Bethe free energyis positive definite, which shows non-convexity for...
متن کاملMIME: Mutual Information Minimization and Entropy Maximization for Bayesian Belief Propagation
Bayesian belief propagation in graphical models has been recently shown to have very close ties to inference methods based in statistical physics. After Yedidia et al. demonstrated that belief propagation fixed points correspond to extrema of the so-called Bethe free energy, Yuille derived a double loop algorithm that is guaranteed to converge to a local minimum of the Bethe free energy. Yuille...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009