A semi-supervised squared-loss mutual information estimator that couples unpaired samples through optimal transport matches full-data estimates using only tens of paired examples.
In: NIPS (2014)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LSMI-Sinkhorn: Semi-supervised Mutual Information Estimation with Optimal Transport
A semi-supervised squared-loss mutual information estimator that couples unpaired samples through optimal transport matches full-data estimates using only tens of paired examples.