Self-supervised encoders prefer isotropic Gaussian latent states because the Information Bottleneck, recast as rate-distortion over the predictive manifold, makes these states optimal for target-neutral representations.
A scale-dependent notion of effective dimension
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Why Self-Supervised Encoders Want to Be Normal
Self-supervised encoders prefer isotropic Gaussian latent states because the Information Bottleneck, recast as rate-distortion over the predictive manifold, makes these states optimal for target-neutral representations.