Concavity of reweighted Kikuchi approximation

10/26/2014
by   Po-Ling Loh, et al.
0

We analyze a reweighted version of the Kikuchi approximation for estimating the log partition function of a product distribution defined over a region graph. We establish sufficient conditions for the concavity of our reweighted objective function in terms of weight assignments in the Kikuchi expansion, and show that a reweighted version of the sum product algorithm applied to the Kikuchi region graph will produce global optima of the Kikuchi approximation whenever the algorithm converges. When the region graph has two layers, corresponding to a Bethe approximation, we show that our sufficient conditions for concavity are also necessary. Finally, we provide an explicit characterization of the polytope of concavity in terms of the cycle structure of the region graph. We conclude with simulations that demonstrate the advantages of the reweighted Kikuchi approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2023

Optimal radio labelings of the Cartesian product of the generalized Peterson graph and tree

A radio labeling of a graph G is a function f : V(G) →{0,1,2,…} such tha...
research
07/04/2012

Sufficient conditions for convergence of Loopy Belief Propagation

We derive novel sufficient conditions for convergence of Loopy Belief Pr...
research
01/09/2018

Sufficient Conditions for the Tightness of Shannon's Capacity Bounds for Two-Way Channels

New sufficient conditions for determining in closed form the capacity re...
research
09/21/2022

Quasipolynomial-time algorithms for repulsive Gibbs point processes

We demonstrate a quasipolynomial-time deterministic approximation algori...
research
07/24/2019

Reducing Path TSP to TSP

We present a black-box reduction from the path version of the Traveling ...
research
01/26/2022

Fourier-Reflexive Partitions and Group of Linear Isometries with Respect to Weighted Poset Metric

Let 𝐇 be the cartesian product of a family of abelian groups indexed by ...
research
07/06/2016

Graphons, mergeons, and so on!

In this work we develop a theory of hierarchical clustering for graphs. ...

Please sign up or login with your details

Forgot password? Click here to reset