
SV
Sergei V. Kalinin
· 1 min read
ResearcharXiv cs.LG
The structure of variational autoencoder latent spaces and its consequences for representation and optimization
arXiv:2611.19972v1 Announce Type: new
Abstract: Variational autoencoders (VAEs) are widely used to build low-dimensional representations of scientific data, with the expectation that regularization yields smooth coordinates for interpolation, generation and optimization. However, applications in microscopy reveal domains, narrow transitions and rare-state islands in VAE latent spaces that smoothness alone does not explain. We show that, for prototype data with squared-error reconstruction and an optimal decoder, the latent-space objective has a direct correspondence with the Flory-Huggins theory of a regular solution, and use it to analyze how the objective, posterior distributions and latent dimensionality organize the representation. Data families occupy domains separated by finite-width walls that broaden with increasing regularization until class separation is lost through posterior collapse. Class centroids behave like particles in a harmonic trap: the prior confines them, and structural dissimilarity sets a soft repulsion that determines which classes become neighbors and how far apart they sit, with separations growing only logarithmically with dissimilarity. Rare states can remain unresolved, form small islands, accumulate within walls or develop intervening domains, depending on their frequency and similarity to common states. The posterior covariance can align domains with the latent axes, but axis alignment does not imply separation of physical factors. Rotations can produce rings and encoder cuts that reflect data symmetry, while insufficient dimensionality can lead to suppression, mixing or folding of additional factors. Comparisons with flow models, deep kernel learning (DKL) and hybrid VAE-DKL models show how these structures change when reconstruction and prediction play different roles. We discuss implications for interpreting data, discovering rare states, generating intermediate states and optimizing properties.
Original source
This story was published by arXiv cs.LG and written by Sergei V. Kalinin. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


