The paper derives the standard closed-form KL divergence between Gaussians with diagonal covariance from the general definition for use in VAE training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective
The paper derives the standard closed-form KL divergence between Gaussians with diagonal covariance from the general definition for use in VAE training.