Neural MI estimators can become reliable in low-latent-dimension settings with a protocol of max-test early stopping, subsampling extrapolation, and probabilistic critics.
Mutual information neural estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.data-an 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accurate Estimation of Mutual Information in High Dimensional Data
Neural MI estimators can become reliable in low-latent-dimension settings with a protocol of max-test early stopping, subsampling extrapolation, and probabilistic critics.