arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.10649cs.LGcs.AIstat.ML

贝叶斯网络的逆

Inversion of Bayesian Networks

Hamburg University of Technology(汉堡工业大学);University of Oxford(牛津大学);Leipzig University(莱比锡大学);Santa Fe Institute(圣塔菲研究所)

Jesse van Oostrum, Peter van Hintum, Nihat Ay

AI总结:

本文在概率图模型与贝叶斯网络框架下,研究识别网络精确表示生成模型真实后验的充要条件,给出基于 d-分离的全局条件及局部条件,并指出完美性的关键作用。

摘要:

变分自编码器和 Helmholtz 机使用识别网络(编码器)来逼近生成模型(解码器)的后验分布。本文研究识别网络能够精确建模真实后验分布所需的充要性质。这些结果是在概率图模型/贝叶斯网络的一般语境下推导的,其中网络表示一组条件独立性陈述。我们推导了识别网络具备所需性质的全局条件(以 d-分离表示)和局部条件。结果表明,对于局部条件而言,完美性(对每个节点,所有父节点都被连接)这一性质起着重要作用。

英文摘要:

Variational autoencoders and Helmholtz machines use a recognition network (encoder) to approximate the posterior distribution of a generative model (decoder). In this paper we study the necessary and sufficient properties of a recognition network so that it can model the true posterior distribution exactly. These results are derived in the general context of probabilistic graphical modelling / Bayesian networks, for which the network represents a set of conditional independence statements. We derive both global conditions, in terms of d-separation, and local conditions for the recognition network to have the desired qualities. It turns out that for the local conditions the property perfectness (for every node, all parents are joined) plays an important role.

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。

↑