Super-resolution meets machine learning: approximation of measures

The problem of super-resolution in general terms is to recuperate a finitely supported measure given finitely many of its coefficients with respect to some orthonormal system. The interesting case concerns situations, where the number of coefficients required is substantially smaller than a power of the reciprocal of the minimal separation among the points in the support of . In this paper, we consider the more severe problem of recuperating approximately without any assumption on beyond having a finite total variation. In particular, may be supported on a continuum, so that the minimal separation among the points in the support of is . A variant of this problem is also of interest in machine learning as well as the inverse problem of de-convolution. We define an appropriate notion of a distance between the target measure and its recuperated version, give an explicit expression for the recuperation operator, and estimate the distance between and its approximation. We show that these estimates are the best possible in many different ways. We also explain why for a finitely supported measure the approximation quality of its recuperation is bounded from below if the amount of information is smaller than what is demanded in the super-resolution problem.
View on arXiv