3 papers
cs.LG2026
A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
Zegu Zhang, Jianhua Peng, Jian Zhang
Posterior collapse in variational autoencoders is often diagnosed by its symptoms: a small KL term, a strong decoder, or weak use of the latent code. These signals are useful, but…
cs.LG2026
RST: certifying and constructing prescribed information in variational autoencoders
Zegu Zhang, Jianhua Peng, Jian Zhang
Posterior-collapse diagnostics can show that a VAE uses its latent representation, but they do not determine whether a specified information view crosses a representation/readout i…
cs.LG2026
Spherical VAE with Cluster-Aware Feasible Regions: Guaranteed Prevention of Posterior Collapse
Zegu Zhang, Jian Zhang
Variational autoencoders (VAEs) frequently suffer from posterior collapse, where the latent variables become uninformative as the approximate posterior degenerates to the prior. Wh…