PT Unknown
AU David Roche
Debora Gil
Jesus Giraldo
TI An inference model for analyzing termination conditions of Evolutionary Algorithms
BT 14th Congrès Català en Intel·ligencia Artificial
PY 2011
BP 216
EP 225
DE Evolutionary Computation Convergence; Termination Conditions; Statistical Inference
AB In real-world problems, it is mandatory to design a termination condition for Evolutionary Algorithms (EAs) ensuring stabilization close to the unknown optimum. Distribution-based quantities are good candidates as far as suitable parameters are used. A main limitation for application to real-world problems is that such parameters strongly depend on the topology of the objective function, as well as, the EA paradigm used.We claim that the termination problem would be fully solved if we had a model measuring to what extent a distribution-based quantity asymptotically behaves like the solution accuracy. We present a regression-prediction model that relates any two given quantities and reports if they can be statistically swapped as termination conditions. Our framework is applied to two issues. First, exploring if the parameters involved in the computation of distribution-based quantities influence their asymptotic behavior. Second, to what extent existing distribution-based quantities can be asymptotically exchanged for the accuracy of the EA solution.
ER