PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

How entropy-theorems can show that approximating high-dim Pareto-fronts is too hard.
Olivier Teytaud
In: PPSN-BTP 2006, 2006, Reykjavik.

Abstract

It is empirically established that multiobjective evolutionary algorithms do not scale well with the nu mber of conflicting objectives. We here show that the convergence rate of any comparison-based multi-obj ective algorithm, for the Hausdorff distance, is not much better than the convergence rate of the random search, unless the number of objectives is very moderate, in a framework in which the stronger assumpti on is that the objectives have conflicts. Our conclusions are (i) the relevance of the number of conflic ting objectives (ii) the relevance of random-search-based criterions (iii) the very-hardness of more tha n 3-objectives optimization (iv) some hints about new cross-over operators.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:2450
Deposited By:Olivier Teytaud
Deposited On:22 November 2006