As per Understanding Posterior Collapse in Generative Latent Variable Modelsdiagonal_normal PPCA flavor (linear VAE) is identical to the global maximum for the marginal log-likelihood of pPCA. That means we can remove multivariate_normal PPCA flavor and leave only diagonal_normal (optionally rename it to linear_vae).
As per Understanding Posterior Collapse in Generative Latent Variable Models
diagonal_normal
PPCA flavor (linear VAE) is identical to the global maximum for the marginal log-likelihood of pPCA. That means we can removemultivariate_normal
PPCA flavor and leave onlydiagonal_normal
(optionally rename it tolinear_vae
).