The Local Geometry of Testing in Ellipses: Tight Control via Localized Kolmogorov Widths

Abstract

Mean testing over ellipses is a decision problem that arises in several applications, including non-parametric goodness-of-fit testing, signal detection in cognitive radio, and regression function testing in reproducing kernel Hilbert spaces. We study the local geometry of such testing problems with compound alternatives. Given samples of a Gaussian random vector, the goal is to distinguish whether the mean is equal to a known vector within an ellipse, or equal to some other unknown vector in the ellipse. While past work on such problems has focused on the difficulty in a global sense, we study difficulty in a way that is localized to each vector within the ellipse. Our main result is to give sharp upper and lower bounds on the localized minimax testing radius in terms of an explicit formula involving the Kolmogorov width of the ellipse intersected with a Euclidean ball. When applied to particular examples, our general theorems yield interesting rates that were not known before: as a particular case, for testing in Sobolev ellipses of smoothness $\alpha $ , we demonstrate rates that vary from $(\sigma ^{2})^{\frac {4 \alpha }{4 \alpha + 1}}$ , corresponding to the classical global rate, to the faster rate $(\sigma ^{2})^{\frac {8 \alpha }{8 \alpha + 1}}$ , achievable for vectors at favorable locations within the ellipse. We also show that the optimal test for this problem is achieved by a linear projection test that is based on an explicit lower-dimensional projection of the observation vector.