53 citations · 89 across the 7 of their papers we have counts for
7 papers
Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters
Sebastian Salwig, Till Kahlke, Florian Hirschberger +2
Gaussian Mixture Models (GMMs) range among the most frequently used models in machine learning. However, training large, general GMMs becomes computationally prohibitive for data s…
The ELBO of Variational Autoencoders Converges to a Sum of Three Entropies
Simon Damm, Dennis Forster, Dmytro Velychko +3
The central objective function of a variational autoencoder (VAE) is its variational lower bound (the ELBO). Here we show that for standard (i.e., Gaussian) VAEs the ELBO converges…
Large Scale Clustering with Variational EM for Gaussian Mixture Models
Florian Hirschberger, Dennis Forster, Jörg Lücke
This paper represents a preliminary (pre-reviewing) version of a sublinear variational algorithm for isotropic Gaussian mixture models (GMMs). Further developments of the algorithm…
Can clustering scale sublinearly with its clusters? A variational EM acceleration of GMMs and -means
Dennis Forster, Jörg Lücke
One iteration of standard -means (i.e., Lloyd's algorithm) or standard EM for Gaussian mixture models (GMMs) scales linearly with the number of clusters , data points , an…
-means as a variational EM approximation of Gaussian mixture models
Jörg Lücke, Dennis Forster
We show that -means (Lloyd's algorithm) is obtained as a special case when truncated variational EM approximations are applied to Gaussian Mixture Models (GMM) with isotropic Ga…
Truncated Variational EM for Semi-Supervised Neural Simpletrons
Dennis Forster, Jörg Lücke
Inference and learning for probabilistic generative networks is often very challenging and typically prevents scalability to as large networks as used for deep discriminative appro…