The KL generalization error in unsupervised learning decomposes exactly into model error, data bias, and variance for e-flat models, with closed-form results for ε-PCA on isotropic Gaussians showing optimal rank at the noise floor and a three-regime phase diagram.
Eigenvalues and condition numbers of random matrices.SIAM Journal on Matrix Analysis and Applications, 9(4):543–560, 1988
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Information-Geometric Decomposition of Generalization Error in Unsupervised Learning
The KL generalization error in unsupervised learning decomposes exactly into model error, data bias, and variance for e-flat models, with closed-form results for ε-PCA on isotropic Gaussians showing optimal rank at the noise floor and a three-regime phase diagram.