ARD-VAE uses a hierarchical prior in the latent space whose per-axis variance is learned from the encoder, and a Jacobian-based relevance score, to identify how many latent dimensions a VAE actually needs.
Disentangling by factorising
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders
ARD-VAE uses a hierarchical prior in the latent space whose per-axis variance is learned from the encoder, and a Jacobian-based relevance score, to identify how many latent dimensions a VAE actually needs.