Frechet Differentiability, $p$-Variation and Uniform Donsker Classes

Bayesian Nonparametrics, Robustness and Frechet Classes

Connections between Bayesian nonparametric inference and the classes of prob-ability measures with known marginals (Frechet classes) are investigated. Inparticular, a class of Dirichlet processes with parameters proportional to prob-ability measures in a Frechet class will be considered.Relations between two statistical characters are then studied, by presentinga...

Stability Properties of Empirical Risk Minimization over Donsker Classes

2 ) converges to zero in probability. Hence, even in the case of multiple minimizers of expected error, as n increases it becomes less and less likely that adding a sample (or a number of samples) to the training set will result in a large jump to a new hypothesis. Moreover, under some assumptions on the entropy of the class, along with an assumption of Komlos-Major-Tusnady type, we derive a po...

Some Properties of Empirical Risk Minimization Over Donsker Classes

We study properties of algorithms which minimize (or almost-minimize) empirical error over a Donsker class of functions. We show that the L2-diameter of the set of almost-minimizers is converging to zero in probability. Therefore, as the number of samples grows, it is becoming unlikely that adding a point (or a number of points) to the training set will result in a large jump (in L2 distance) t...

Functions of bounded variation and differentiability

Uniform Glivenko–Cantelli Classes

A class of sets, or functions, is said to be P–Glivenko–Cantelli if the empirical measure Pn converges in some sense to the true measure, P , as n → ∞, uniformly over the class of sets or functions. Thus, the notions of Glivenko–Cantelli, and likewise uniform Glivenko–Cantelli are for the most part qualitative assessments of how “well–behaved” a collection of sets or functions is, in the sense ...