Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations

05/04/2020
by   Tomáš Pevný, et al.
3

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/11/2021

Exchangeability-Aware Sum-Product Networks

Sum-Product Networks (SPNs) are expressive probabilistic models that pro...
research
03/25/2021

Beyond permutation equivariance in graph networks

We introduce a novel architecture for graph networks which is equivarian...
research
01/19/2017

Online Structure Learning for Sum-Product Networks with Gaussian Leaves

Sum-product networks have recently emerged as an attractive representati...
research
05/07/2019

Sum-of-Squares Polynomial Flow

Triangular map is a recent construct in probability theory that allows o...
research
05/05/2020

Classification-Based Anomaly Detection for General Data

Anomaly detection, finding patterns that substantially deviate from thos...
research
06/08/2022

Progress Report: A Deep Learning Guided Exploration of Affine Unimodular Loop Transformations

In this paper, we present a work in progress about a deep learning based...
research
09/07/2018

Dirichlet process mixtures under affine transformations of the data

Location-scale Dirichlet process mixtures of Gaussians (DPM-G) have prov...

Please sign up or login with your details

Forgot password? Click here to reset