Robust Expected Information Gain for Optimal Bayesian Experimental Design Using Ambiguity Sets.
Jinwoo GoTobin IsaacPublished in: CoRR (2022)
Keyphrases
- information gain
- experimental design
- feature selection
- decision trees
- chi squared
- mutual information
- text categorization
- active learning
- feature subset
- correlation coefficient
- sample size
- empirical studies
- naive bayes
- unsupervised learning
- k nearest neighbor
- data mining
- worst case
- learning process
- optimal solution
- bayesian networks
- genetic algorithm