Skip to main content

🏢 University of Klagenfurt

Mutual Information Estimation via $f$-Divergence and Data Derangements
·3089 words·15 mins· loading · loading
Machine Learning Deep Learning 🏢 University of Klagenfurt
f-DIME: a novel class of discriminative mutual information estimators using f-divergence outperforms state-of-the-art methods by achieving an excellent bias-variance trade-off. This is achieved throug…