Avoiding Latent Variable Collapse With Generative Skip Models
international conference on artificial intelligence and statistics, 2018.
Variational autoencoders (VAEs) learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture complex distributions, but they can also suffer from an issue known as variable collapse, especially if the lik...More
PPT (Upload PPT)