In information theory, the information projection or I-projection of a probability distribution q onto a set of distributions P is
where
The I-projection is useful in setting up information geometry, notably because of the following inequality:
This inequality can be interpreted as an information-geometric version of Pythagoras' triangle inequality theorem, where KL divergence is viewed as squared distance in a Euclidean space.
It is worthwhile to note that since
The reverse I-projection is