Belief Propagation on Replica Symmetric Random Factor Graph Models

Belief Propagation on Replica Symmetric Random Factor Graph Models
复制标题

复制对称随机因子图模型上的置信传播

DOI:
--
复制
发表时间:
2016
期刊:
International Workshop and International Workshop on Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques
影响因子:
--
通讯作者:
Will Perkins
Will Perkins
中科院分区:
--
文献类型:
--
作者:
A. Coja;Will Perkins

文献摘要

参考文献

被引文献

相似文献

根据物理学预测,满足某种“静态副本对称”条件的随机因子图模型的自由能可以通过Belief Propagation消息传递方案来计算[Krzakala等人,PNAS 2007]。在这里,我们证明了这一猜想的两个一般类的随机因子图模型,即泊松随机因子图和随机正则因子图。具体而言,我们证明了构造的消息,就像在无环因子图的情况下渐近满足的信念传播方程和自由能密度给出的贝特自由能公式。
According to physics predictions, the free energy of random factor graph models that satisfy a certain "static replica symmetry" condition can be calculated via the Belief Propagation message passing scheme [Krzakala et al., PNAS 2007]. Here we prove this conjecture for two general classes of random factor graph models, namely Poisson random factor graphs and random regular factor graphs. Specifically, we show that the messages constructed just as in the case of acyclic factor graphs asymptotically satisfy the Belief Propagation equations and that the free energy density is given by the Bethe free energy formula.
随机图着色的局部收敛
DOI: 10.1007/s00493-016-3394-x
发表时间: 2018
期刊: Combinatorica
影响因子: 1.1
作者:
A. Coja-Oghlan;C. Efthymiou;N. Jafaari
通讯作者: N. Jafaari