PGMO PHD Awards 2017
Publiée le 2017-07-10
Les lauréats 2017 du prix de thèse PGMO sont...
"This thesis contains pathbreaking and practically very important results concerning local search heuristics for clustering (k-means, k-median) and network design (traveling salesman, Steiner tree). It establishes some structural properties under which these local search heuristics perform very well and even yield polynomial time approximation schemes for these problems."
&
"The thesis begins with a remarkably clear presentation of the basics of online linear optimization, regret minimization, mirror descent and approachability. The author develops the analysis of the classical problem of prediction with expert advice in which the outcome vector is assumed to be sparse, and design of optimal approachability strategies for the problem of prediction under partial monitoring. The author also shows how a continuous mirror descent motivates a large set of minimization algorithms in discrete time and the thesis ends with an elegant result bounding variations of convex functions."
Le jury pour l'édition 2017 était présidé par Guillaume Carlier et composé de :
Membres désignés par la ROADEF
- Clarisse Dhaenens, CRIStAL, Université de Lille
- Marcel Mongeau, ENAC
- Sourour Elloumi, ENSTA
Membres désignés par le groupe SMAI-MODE
- Guillaume Carlier, CEREMADE (Président)
- Anatoli Juditsky, Laboratoire Jean Kuntzmann, Grenoble
- Jalal Fadili, ENSICAEN
Membres désignés par le Conseil Scientifique du PGMO
- Luce Brotcorne, INRIA Lille
- Julien Mairal, INRIA Grenoble
- Jérôme Renault, Toulouse School of Economics
