Alain Célisse

Stability revisited: new generalisation bounds for the Leave-one-Out

2016 · arXiv (Cornell University)

The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion …

A One-Sample Test for Normality with Kernel Methods

2015 · arXiv (Cornell University)

We propose a new one-sample test for normality in a Reproducing Kernel Hilbert Space (RKHS). Namely, we test the null-hypothesis of belonging to a given family of Gaussian distributions. Hence our procedure may be applied …