Timezone: »

 
Poster
Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay
Frederic Koehler

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #174
in Probabilistic Methods -- Belief Propagation » 
Belief propagation is a fundamental message-passing algorithm for probabilistic reasoning and inference in graphical models. While it is known to be exact on trees, in most applications belief propagation is run on graphs with cycles. Understanding
the behavior of ``loopy'' belief propagation has been a major challenge for researchers in machine learning and other fields, and positive convergence results for BP are known under strong assumptions which imply the underlying graphical model exhibits decay of correlations. We show, building on previous work of Dembo and Montanari, that under a natural initialization BP converges quickly to the global optimum of the Bethe free energy for Ising models on arbitrary graphs, as long as the Ising model is \emph{ferromagnetic} (i.e. neighbors prefer to be aligned). This holds even though such models can exhibit long range correlations and may have multiple suboptimal BP fixed points. We also show an analogous result for iterating the (naive) mean-field equations; perhaps surprisingly, both results are dimension-free in the sense that a constant number of iterations already provides a good estimate to the Bethe/mean-field free energy.
Keywords: Theory · Probabilistic Methods -> Graphical Models; Probabilistic Methods -> Variational Inference; Theory -> Learning Theory; Theory
[ Paper]  [ Slides] 

Author Information

Frederic Koehler (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors