2024
$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
ICLR 2024poster
The variational autoencoder (VAE) typically employs a standard normal prior as a regularizer for the probabilistic latent encoder. However, the Gaussian tail often decays too quickly to effectively accommodate the encoded points, failing to preserve crucial structures hidden in the data. In this pap…