Français Anglais
Accueil Annuaire Plan du site
Accueil > News du laboratoire > Séminaire Digiteo/CDS, 26/3/2015, 14:30,Gàbor LUGOSI
Séminaire Digiteo/CDS, 26/3/2015, 14:30,Gàbor LUGOSI
Séminaire Digiteo/CDS, 26/3/2015, 14:30,Gàbor LUGOSI Séminaire Digiteo/CDS, 26/3/2015, 14:30,Gàbor LUGOSI
26 mars 2015

Titre : Looking for Adam in a tree
Conférencier : Gàbor LUGOSI, ICREA Research Professor, Barcelona,
26/3/2015, 14:30, Amphi Digiteo Moulon (Bât 660)
Abstract : We discuss algorithms to find the first vertex in large random trees generated by either the uniform attachment or preferential attachment model. We require the algorithm to output a set of K vertices, such that, with probability at least 1 − ε, the first vertex is in this set. We show that for any ε, there exist such algorithms with K independent of the size of the tree. The talk is based on joint work with Seb Bubeck and Luc Devroye. 
 
Bio :
Gábor Lugosi is an ICREA Research Professor at the Department of
Economics and Business at Pompeu Fabra University.

His research has mostly focused on mathematical aspects of machine
learning including classification, density estimation,
regression, but also clustering and data compression, ranking, and
sequential prediction. He is also interested in concentration inequalities
and understanding the behavior of large random structures such as
random graphs and networks.

He has co-authored four research monographs; one on classification
(published by Springer in 1996), one on density estimation (also
Spinger, 2001a) , one on sequential prediction (Cambridge University
Press, 2006), and one on concentration inequalities (Oxford University
Press, 2013).
 
News
George Manoussakis, lauréat 2018, prix de thèse (accessit) Charles Delorme
18 septembre 2018
George Manoussakis, est lauréat de prix de thèse (accessit) Ch. Delorme 2018. Il a soutenu sa thèse au LRI/Galac en Novembre 2017 sous la direction de J. Cohen et A. Deza. Depuis Septembre 2018 il est MdeC à l'Université de Versailles/Li-PaRAD.

TrackML dans Nature
21 janvier 2018
L'apprentissage automatique peut-il aider la physique des hautes énergies à découvrir et à caractériser de nouvelles particules ? TAO participe à l'organisation du challenge TrackML avec le CERN. La seconde phase de la compétition utilisera Codalab.

Un article de Isabelle Guyon sur la démocratisation de l'IA
19 mars 2018
Lien vers l'article paru dans le journal le monde :
http://www.lemonde.fr/acces-restreint/sciences/article/2018/04/08/a4544bd07cad09fe52980c0f82c08b34_5282548_1650684.html