离散最大熵分布的均值多面体张量网络表示
Tensor network representations of discrete maximum entropy distributions via mean polytopes
浏览论文内容
中文总结 AI 辅助
本文提出CompActNets张量网络架构,利用均值多面体几何表示离散最大熵分布,并揭示张量网络秩与面复杂度及命题公式的联系。
中文摘要 AI 辅助
我们提出了在期望约束下离散最大熵分布的张量网络表示。为此,我们引入了计算激活网络(CompActNets),这是一种包含指数族的张量网络架构。通过利用可实现期望向量凸多面体的几何性质,我们在同一架构中表示任意最大熵分布。我们利用该多面体的真面对应于指数族的边界闭包这一事实,这限制了分布的支撑集。然后,我们在CompActNet架构中推导出支撑集的显式表示。所提出的框架表明张量网络秩可作为面的复杂度度量。最后,一个关于布尔统计的案例研究将0/1-多面体的几何性质直接与命题公式联系起来。
英文摘要
We present tensor network representations for discrete maximum entropy distributions under expectation constraints. To this end, we introduce Computation-Activation Networks (CompActNets), a tensor network architecture that subsumes exponential families. By leveraging the geometry of the convex polytope of realizable expectation vectors, we represent any maximum entropy distribution in the same architecture. We exploit the fact that proper faces of this polytope correspond to the boundary closure of exponential families, which restricts the distribution's support. We then derive explicit representations for the support within the CompActNet architecture. The proposed framework suggests tensor network ranks as complexity measures for faces. Finally, a case study on Boolean statistics links the geometry of 0/1-polytopes directly to propositional formulas.
发表机构
- Weierstrass Institute of Applied Analysis and Stochastics(魏尔斯特拉斯应用分析与随机学研究所)
机构由 AI 辅助整理,请以论文原文为准。