The variational lower bound (a.k.a. ELBO or free energy) is the central
...
We combine two popular optimization approaches to derive learning algori...
Discrete latent variables are considered important for real world data, ...
The central objective function of a variational autoencoder (VAE) is its...
The data model of standard sparse coding assumes a weighted linear summa...
We combine two recent lines of research on sublinear clustering to
signi...
We investigate the optimization of two generative models with binary hid...
One iteration of k-means or EM for Gaussian mixture models (GMMs) scales...
We show that k-means (Lloyd's algorithm) is equivalent to a variational ...
Inference and learning for probabilistic generative networks is often ve...
We derive a novel variational expectation maximization approach based on...
Classifiers for the semi-supervised setting often combine strong supervi...
We study inference and learning based on a sparse coding model with
`spi...
We study the task of cleaning scanned text documents that are strongly
c...
We define and discuss the first sparse coding algorithm based on closed-...