Modern data analysis provides scientists with statistical and machine learning algorithms with impressive performance. In front of their extensive use to tackle problems of constantly growing complexity, there is a real need to understand the conditions under which algorithms are successful or bound to fail. An additional objective is to gain insights into the design of new algorithmic methods able to tackle more innovative and challenging tasks. A natural framework for developing a mathematical theory of these methods is extit{nonparametric inference}. This area of Statistics is concerned with inferences of unknown quantities of interest under minimal assumptions, less restrictive than classical (parametric) statistics. The common thread i...