Information projections have found important applications in probability theory, statistics, and related areas. In the field of hypothesis testing in particular, the reverse information projection (RIPr) has recently been shown to lead to so-called growth-rate optimal (GRO) e-statistics for testing simple alternatives against composite null hypotheses. However, the RIPr as well as the GRO criterion are undefined whenever the infimum information divergence between the null and alternative is infinite. We show that in such scenarios there often still exists an element in the alternative that is 'closest' to the null: the universal reverse information projection. The universal reverse information projection and its non-universal counterpart coincide whenever information divergence is finite. Furthermore, the universal RIPr is shown to lead to optimal e-statistics in a sense that is a novel, but natural, extension of the GRO criterion. We also give conditions under which the universal RIPr is a strict sub-probability distribution, as well as conditions under which an approximation of the universal RIPr leads to approximate e-statistics. For this case we provide tight relations between the corresponding approximation rates.
翻译:暂无翻译