Hypothesis testing with active information
arXiv:2011.04834 · doi:10.1016/j.spl.2020.108742
Abstract
We develop hypothesis testing for active information -the averaged quantity in the Kullback-Liebler divergence. To our knowledge, this is the first paper to derive exact probabilities of type-I errors for hypothesis testing in the area.
Typo changed in one of the names in the Metadata, and a reference to an equation from the paper in the Supplement