Accueil > EQUIPES > Statistique, Probabilités, Optimisation et Contrôle > Séminaires de l’équipe


Les responsables du séminaire sont Alexandre Cabot et Yoann Offret

  • Le séminaire a lieu habituellement le mercredi 10h30-11h30 en salle 318

les prochaines séances planifiées sont listées ci-dessous, tandis que les séances qui ont déjà eu lieu sont consultables sur la page d’archives

Séminaires SPOC

Mercredi 23 mai 10:30-11:30 - Mathurin Massias

Celer : un solveur rapide pour Lasso avec extrapolation duale

Résumé : Convex sparsity-inducing regularizations are ubiquitous in high-dimension machine learning, but their non-differentiability requires the use of iterative solvers. To accelerate such solvers, state-of-the-art approaches consist in reducing the size of the optimization problem at hand. In the context of regression, this can be achieved either by discarding irrelevant features (screening techniques) or by prioritizing features likely to be included in the support of the solution (working set techniques). Duality comes into play at several steps in these techniques.
Here, we propose an extrapolation technique starting from a sequence of iterates in the dual that leads to the construction of an improved dual point. This enables a tighter control of optimality as used in stopping criterion, as well as better screening performance of Gap Safe rules. Finally, we propose a working set strategy based on an aggressive use of Gap Safe rules and our new dual point construction, which improves state-of-the-art time performance on Lasso problems.

Séminaires SPOC

Mercredi 13 juin 10:30-11:30 - Nicolas Tremblay - Laboratoire GIPSA, Grenoble

Filtering and sampling of graph signals, and its application to clustering

Résumé : Spectral clustering has become a popular technique due to its high performance in many contexts. It comprises three main steps : create a similarity graph between N objects to cluster, compute the first k eigenvectors of its Laplacian matrix to define a feature vector for each object, and run k-means on these features to separate objects into k classes. Each of these three steps becomes computationally intensive for large N and/or k. We propose to speed up the last two steps based on recent results in the emerging field of graph signal processing : graph filtering of random signals, and random sampling of bandlimited graph signals. In this presentation, we will take time to go over what filtering and sampling mean for a signal defined on a graph, and explain to what extent they can prove useful for spectral clustering.

Séminaires SPOC

Mercredi 27 juin 10:30-11:30 - Nicolas Keriven