Statistics/Learning at Paris-Saclay

vendredi 8 janv. 2016, 09:00 → 18:30 Europe/Paris

Centre de Conférences Marilyn et James Simons (Le Bois-Marie)

The aim of this workshop is to bring together mathematicians and computer scientists around some talks on recent results in statistics and machine learning. Various topics will be presented, among which sequential learning, aggregation of estimators, Hidden Markov models, network inference and optimization for machine learning.

Organised by : Sylvain ARLOT

Invited speakers :

Pierre Alquier (ENSAE)
Stéphane Gaiffas (Ecole Polytechnique)
Claire Lacour (Université Paris-Sud)
Odalric-Ambrym Maillard (INRIA - Université Paris-Sud)
Yann Ollivier (CNRS - Université Paris-Sud)
Joseph Salmon (LTCI, CNRS, Télécom ParisTech)

 

 

Abstracts abstracts.pdf

Poster poster_arlot.pdf

PowerPoint Alquier alquier.pdf

PowerPoint Gaiffas gaiffas.pdf

PowerPoint Lacour lacour.pdf

PowerPoint Maillard maillard.pdf

PowerPoint Salmon salmon.pdf

Journée Statistique: Apprentissage Paris-Saclay¶

09:00 Café d'accueil

1 Pierre Alquier¶

PAC-Bayesian bounds for aggregation of estimators: introduction and computational issues

Transparents alquier.pdf

10:50 Pause Café

2 Joseph Salmon¶

GAP safe screening rule for sparsity enforcing penalties

Transparents salmon.pdf

3 Odalric-Ambrym Maillard¶

Multi-armed bandits: Proof techniques and challenges

Transparents maillard.pdf

13:00 Déjeuner

4 Claire Lacour¶

Minimax adaptive estimation of nonparametric hidden Markov models

Transparents lacour.pdf

5 Stéphane Gaiffas¶

Concentration for matrix martingales and microscopic activity of social networks using Hawkes processes

Transparents gaiffas.pdf

16:10 Pause café

6 Yann Ollivier¶

Learn as you go: Training recurrent neural networks and dynamical systems

17:30 Discussion