Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
Proceedings of the 10th International Conference on Probabilistic Graphical Models, PMLR 138:341-352, 2020.
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 and optimize 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 pushes the state-of-the-art on the density estimation task on used datasets.