Journée Doctorant·e·s Rennais·e·s en Statistique - 2024

Session

Statistique théorique

18 mars 2024, 15:45

Amphi Lebesgue (IRMAR)

1. Discrete Optimization Methods for l0-norm Problems

Theo Guyard (INSA Rennes / INRIA Rennes)

18/03/2024 15:45

Sparse linear models are ubiquitous in various applied mathematical fields such as high-dimensional statistics, machine learning and signal processing, among many others. Constructing such models can be done via the resolution of optimization problems of the form
\begin{equation}
\label{prob}
\tag{$\mathcal{P}$}
\textstyle\min_{\mathbf{x} \in \mathbf{R}^{n}} \ f(\mathbf{x}) +...

5. Directional regularity: Achieving faster rates of convergence in multivariate functional data

M. Omar Kassi (ENSAI)

18/03/2024 16:05

We introduce a new notion of regularity, called directional regularity, which is rele- vant for a wide range of applications involving multivariate functional data. We show that for anisotropic functional data, faster rates of convergence can be obtained by adapting to its directional regularity through a change of basis. An algorithm is constructed for the estimation and identification of the...