Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
arXiv:2005.01297
Abstract
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.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Variational Inference with Normalizing Flows
- Normalizing Flows: An Introduction and Review of Current Methods
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Sum-Product Networks: A New Deep Architecture
- Normalizing Flows for Probabilistic Modeling and Inference
- Improving Variational Auto-Encoders using Householder Flow
- Invert to Learn to Invert
- Are generative deep models for novelty detection truly better?
- Learning Graph-Structured Sum-Product Networks for Probabilistic Semantic Maps