Tracking property of UMDA in dynamic environment by landscape framework

Authors:
Ran Long;Liangqi Gong;Bo Yuan;Ping Ao;Qingsheng Ren
Affiliations:
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China;Shanghai Center for Systems Biomedicine, Shanghai Jiao Tong University, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III
Year:
2012

Citing 6
Cited 0

Nonstationary function optimization using genetic algorithm with dominance and diploidy

Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Evolutionary computation and Wright's equation

Theoretical Computer Science - Natural computing
Optimal Mutation Rate Using Bayesian Priors for Estimation of Distribution Algorithms

SAGA '01 Proceedings of the International Symposium on Stochastic Algorithms: Foundations and Applications
Genetic Algorithms and Flowshop Scheduling: Towards the Development of a Real-Time Process Control System

Selected Papers from AISB Workshop on Evolutionary Computing
Analysis of the (1+1) EA for a dynamically bitwise changing ONEMAX

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Evolutionary optimization in uncertain environments-a survey

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, the landscape framework is used to analysis the tracking performance of univariate marginal distribution algorithm (UMDA) in dynamic environment. A set of stochastic differential equations (SDEs) is used to describe the evolutionary dynamics of the algorithm. The corresponding potential function is constructed from these SDEs. Dynamic mean first passage time, which is a new concept, is defined as the time it takes from an optimum to another in a dynamic environment. This concept can be used to measure the tracking property of the algorithm.