论文标题
Sum-Propoduct-Transform网络：使用可逆转换利用对称性
Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
论文作者
论文摘要
在这项工作中，我们提出了Sum-Prododuct-Transform网络（SPTN），这是使用可逆转换作为其他内部节点的总和网络的扩展。转换的类型和位置通过许多有趣的特殊情况确定了所得SPTN的特性。重要的是，具有高斯叶子和仿射转化的SPTN构成了可以在SPN中有效计算的推理任务。我们建议使用一组吉文族旋转对单位矩阵的有效参数化将仿射转化存储在其SVD分解中。最后但并非最不重要的一点是，我们证明了G-SPTN在密度估计任务上实现最新结果，并且具有针对异常检测的最新方法具有竞争力。
In this work, we propose Sum-Product-Transform Networks (SPTN), an extension of sum-product networks that uses invertible transformations as additional internal nodes. The type and placement of transformations determine properties of the resulting SPTN with many interesting special cases. Importantly, SPTN with Gaussian leaves and affine transformations pose the same inference task tractable that can be computed efficiently in SPNs. We propose to store affine transformations in their SVD decompositions using an efficient parametrization of unitary matrices by a set of Givens rotations. Last but not least, we demonstrate that G-SPTNs achieve state-of-the-art results on the density estimation task and are competitive with state-of-the-art methods for anomaly detection.
