VIG, defined as the difference between marginal and conditional Vendi entropy, is proposed as a sample-based, similarity-aware alternative to mutual information, with applications in active learning and level-set estimation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vendi Information Gain: An Alternative To Mutual Information For Science And Machine Learning
VIG, defined as the difference between marginal and conditional Vendi entropy, is proposed as a sample-based, similarity-aware alternative to mutual information, with applications in active learning and level-set estimation.