English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Variational autoencoders (VAEs) are one of the deep generative models thathave experienced enormous success over the past decades. However, in practice,they suffer from a problem called posterior collapse, which occurs when theencoder coincides, or collapses, with the prior taking no information from thelatent structure of the input data into consideration. In this work, weintroduce an inverse Lipschitz neural network into the decoder and, based onthis architecture, provide a new method that can control in a simple and clearmanner the degree of posterior collapse for a wide range of VAE models equippedwith a concrete theoretical guarantee. We also illustrate the effectiveness ofour method through several numerical experiments.

Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network