Inexact generative models stay on the data manifold because infinitesimal learning errors perturb the density only along the manifold, when top Lyapunov vectors align with the support boundary.
Estimating the support of a high-dimensional distribution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When and how can inexact generative models still sample from the data manifold?
Inexact generative models stay on the data manifold because infinitesimal learning errors perturb the density only along the manifold, when top Lyapunov vectors align with the support boundary.