4 papers · 1 filter
Disentanglement of Sources in a Multi-Stream Variational Autoencoder
Veranika Boukun, Jörg Lücke
Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled repres…
Generative Models with ELBOs Converging to Entropy Sums
Jan Warnken, Dmytro Velychko, Simon Damm +2
The evidence lower bound (ELBO) is one of the most central objectives for probabilistic unsupervised learning. For the ELBOs of several generative models and model classes, we here…
On the Convergence of the ELBO to Entropy Sums
Jörg Lücke, Jan Warnken
The variational lower bound (a.k.a. ELBO or free energy) is the central objective for many established as well as for many novel algorithms for unsupervised learning. Such algorith…
Learning Sparse Codes with Entropy-Based ELBOs
Dmytro Velychko, Simon Damm, Asja Fischer +1
Standard probabilistic sparse coding assumes a Laplace prior, a linear mapping from latents to observables, and Gaussian observable distributions. We here derive a solely entropy-b…