This PhD project is proposed in the context of the Continuous Optimization research theme of the TAO Machine Learning and Optimization group at the LRI. We seek to develop and benchmark stochastic search methods for high-dimensional continuous black-box optimization problems in search spaces with between thousands and millions of variables. The methods to be developed are based on modern evolutionary algorithms that sample new candidate search points from a probability distribution. However, for developing efficient algorithms in very high dimensions, the question of variable-, feature-, and subspace-selection becomes important and will play an instrumental role. In order to evaluate new algorithms, a generally applicable benchmark testbeds for high dimensional black-box optimization problems will be developed and implemented.
Context
Objectives
Work program
Extra information
Prerequisite
Détails
Expected funding
Institutional funding
Status of funding
Expected
Candidates
Ouassim AIT ELHARA
Utilisateur
nikolaus.hansen
Créé
Mercredi 06 juin 2012 20:08:00 CEST
dernière modif.
Mercredi 06 juin 2012 20:08:00 CEST
Fichiers joints
filename
créé
hits
filesize
Aucun fichier joint à cette fiche
Connexion
Ecole Doctorale Informatique Paris-Sud
Directrice
Nicole Bidoit Assistante
Stéphanie Druetta Conseiller aux thèses
Dominique Gouyou-Beauchamps
ED 427 - Université Paris-Sud
UFR Sciences Orsay
Bat 650 - aile nord - 417
Tel : 01 69 15 63 19
Fax : 01 69 15 63 87
courriel: ed-info à lri.fr