$\alpha$ Belief Propagation as Fully Factorized Approximation

Autor:	Liu, Dong, Moghadam, Nima N., Rasmussen, Lars K., Huang, Jinliang, Chatterjee, Saikat
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Belief propagation (BP) can do exact inference in loop-free graphs, but its performance could be poor in graphs with loops, and the understanding of its solution is limited. This work gives an interpretable belief propagation rule that is actually minimization of a localized $\alpha$-divergence. We term this algorithm as $\alpha$ belief propagation ($\alpha$-BP). The performance of $\alpha$-BP is tested in MAP (maximum a posterior) inference problems, where $\alpha$-BP can outperform (loopy) BP by a significant margin even in fully-connected graphs. Comment: GlobalSIP 2019
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1908.08906 Zobrazit plný text záznamu View this record from Arxiv