Experiments show low mutual information does not reliably correspond to geometric compression via class-wise clustering in CEB and dropout networks; the negative nonlinear link can reverse with training changes, suggesting generalization confounds the connection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometric and Information Compression of Representations in Deep Learning
Experiments show low mutual information does not reliably correspond to geometric compression via class-wise clustering in CEB and dropout networks; the negative nonlinear link can reverse with training changes, suggesting generalization confounds the connection.