3 citations · 10 across the 4 of their papers we have counts for
6 papers
Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
Tomas Pevny, Vasek Smidl, Martin Trapp +2
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…
DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models
Mohamed Tarek, Kai Xu, Martin Trapp +2
We present the preliminary high-level design and features of DynamicPPL.jl, a modular library providing a lightning-fast infrastructure for probabilistic programming. Besides a com…
Deep Structured Mixtures of Gaussian Processes
Martin Trapp, Robert Peharz, Franz Pernkopf +1
Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs. In order to i…
Optimisation of Overparametrized Sum-Product Networks
Martin Trapp, Robert Peharz, Franz Pernkopf
It seems to be a pearl of conventional wisdom that parameter learning in deep sum-product networks is surprisingly fast compared to shallow mixture models. This paper examines the…
Bayesian Learning of Sum-Product Networks
Martin Trapp, Robert Peharz, Hong Ge +2
Sum-product networks (SPNs) are flexible density estimators and have received significant attention due to their attractive inference properties. While parameter learning in SPNs i…
Safe Semi-Supervised Learning of Sum-Product Networks
Martin Trapp, Tamas Madl, Robert Peharz +2
In several domains obtaining class annotations is expensive while at the same time unlabelled data are abundant. While most semi-supervised approaches enforce restrictive assumptio…