2 papers
cs.LG2026
-VAEs as Effective Theories: Tolerance-Dependent Dimension
Johannes Hirn
In a -VAE, increasing the regularization strength acts as a spectral cutoff by collapsing low-utility latent coordinates. In the linear Gaussian VAE, the collapse order matches…
cs.LG2026
Latent Spectroscopy: Posterior Collapse as a Feature
Johannes Hirn
We show that, in linear Gaussian VAEs, posterior collapse is a form of latent feature selection. Feature importance is set by each latent coordinate's contribution to reconstructio…