We study the behavior of error bounds for multiclass classification unde...
Kernel methods provide a principled approach to nonparametric learning. ...
Compressive learning is an approach to efficient large scale learning ba...
Characterizing the function spaces corresponding to neural networks can
...
In this work, we consider the linear inverse problem y=Ax+ϵ, where
A X→ ...
We study a natural extension of classical empirical risk minimization, w...
We study the learning properties of nonparametric ridge-less least squar...
We propose and study a multi-scale approach to vector quantization. We
d...
We study reproducing kernel Hilbert spaces
(RKHS) on a Riemannian mani...
Despite recent advances in regularisation theory, the issue of parameter...
Shearlets are a relatively new directional multi-scale framework for sig...
We consider the problem of learning a set from random samples. We show h...