arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.09051math.OCcs.AImath.CO
收藏

在一般高阶图模型中使用线性规划进行精确MAP推断

A polynomial time algebraic solution to exact marginal inference in Markov Random Field models

Ikhlef Bechar

AI总结:

本文提出通过线性规划松弛方法实现一般高阶图模型的精确MAP推断,引入delta分布和正交投影框架,开发了期望优化框架和传统LP松弛方法,从而在一般假设下解决MAP推断问题。

摘要:

本文关注通过传统线性规划松弛方法在一般高阶图模型中实现精确MAP推断的问题。我们开发的证明是一个相对简单的代数证明,主要通过引入两个新的代数工具来实现。一方面,我们引入delta分布,表示两个任意概率分布的差,主要目的是缓解传统概率分布中的符号约束。另一方面,我们通过正交投影框架近似一般离散函数,利用线性组合的函数边际表达,尽管我们更利用后者从全局视角建模局部一致的离散函数集。之后,我们首先从头开发了期望优化框架,即在随机基础上对凸包方法的重新表述,其次开发了该期望优化方法的传统LP松弛方法,并证明其在一般假设下能够解决图模型中的MAP推断问题。最后,我们描述了一个算法,允许从所提出LP松弛的可能分数最优(概率)解中计算精确的MAP解。

英文摘要:

This paper develops on algebraic grounds a polynomial time exact linear solution to the hard combinatorial problem of marginal inference in Markov random field (MRF) models under general assumptions. To prove our claim, we first implicitly remodel a MRF joint distribution as the unique solution of some linear identity assuming its clique potential functions (equivalently, its individual conditional distributions) to be specified. Then, by assuming an arbitrary point subset, we relax accordingly such a (global) linear identity for deriving a second linear identity, solely, acting on a polynomial time number of entries (e.g.; local marginals or Fourier frequencies) of a solution. Then, we show, only using linear algebraic techniques, that such an identity enables to capture all the entries necessary for the exact reconstruction of an MRF marginal distribution, thus, allowing to solve for the latter, exactly and in polynomial time, using a standard linear solver. Last, but not least, this paper probably solves, once and for all, the P = NP conjecture.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑