arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11876cs.AImath.OC
收藏

区域化优化

Regionalized Optimization

Univ. Artois(阿图瓦大学)

Grégoire Sergeant-Perthuis

摘要:

我们提出了一个理论框架,用于在函子的约束下从局部损失的集合中非冗余地重建全局损失;我们将这种损失称为区域化损失,以纪念Yedidia,Freeman,Weiss的著名文章“构建自由能近似和广义置信传播算法”,其中构建了区域化损失的第一个例子,用于熵和边际函子。我们展示了如何可以关联到这些区域化的损失消息传递算法,找到他们的临界点。它是优化问题的一个自然数学框架,其中数据集上有多个观点,并取代消息传递算法作为寻找这些问题的最优解的规范方法。我们解释了广义置信传播算法如何落入我们提出的框架,并提出了新的消息传递算法的嘈杂的信道网络。

英文摘要:

We propose a theoretical framework for non redundant reconstruction of a global loss from a collection of local ones under constraints given by a functor; we call this loss the regionalized loss in honor to Yedidia, Freeman, Weiss' celebrated article `Constructing free-energy approximations and generalized belief propagation algorithms' where a first example of regionalized loss, for entropy and the marginal functor, is built. We show how one can associate to these regionalized losses message passing algorithms for finding their critical points. It is a natural mathematical framework for optimization problems where there are multiple points of views on a dataset and replaces message passing algorithms as canonical ways of finding the optima of these problems. We explain how Generalized Belief propagation algorithms fall into the framework we propose and propose novel message passing algorithms for noisy channel networks.

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。

↑