TY - GEN
T1 - Incorporating a metropolis method in a distribution estimation using markov random field algorithm
AU - Shakya, Siddhartha K.
AU - McCall, John A.W.
AU - Brown, Deryck F.
PY - 2005
Y1 - 2005
N2 - Markov Random Field (MRF) modelling techniques have been recently proposed as a novel approach to probabilistic modelling for Estimation of Distribution Algorithms (EDAs)[34, 4]. An EDA using this technique, presented in [34], was called Distribution Estimation using Markov Random Fields (DEUM). DEUM was later extended to DEUMd [32, 33]. DEUM and DEUMd use a univariate model of probability distribution, and have been shown to perform better than other univariate EDAs for a range of optimization problems. This paper extends DEUMd to incorporate a simple Metropolis method and empirically shows that for linear univariate problems the proposed univariate MRF models are very effective. In particular, the proposed DEUMd algorithm can find the solution in O(n) fitness evaluations. Furthermore, we suggest that the Metropolis method can also be used to extend the DEUM approach to multivariate problems.
AB - Markov Random Field (MRF) modelling techniques have been recently proposed as a novel approach to probabilistic modelling for Estimation of Distribution Algorithms (EDAs)[34, 4]. An EDA using this technique, presented in [34], was called Distribution Estimation using Markov Random Fields (DEUM). DEUM was later extended to DEUMd [32, 33]. DEUM and DEUMd use a univariate model of probability distribution, and have been shown to perform better than other univariate EDAs for a range of optimization problems. This paper extends DEUMd to incorporate a simple Metropolis method and empirically shows that for linear univariate problems the proposed univariate MRF models are very effective. In particular, the proposed DEUMd algorithm can find the solution in O(n) fitness evaluations. Furthermore, we suggest that the Metropolis method can also be used to extend the DEUM approach to multivariate problems.
UR - http://www.scopus.com/inward/record.url?scp=27144449634&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:27144449634
SN - 0780393635
T3 - 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings
SP - 2576
EP - 2583
BT - 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005. Proceedings
T2 - 2005 IEEE Congress on Evolutionary Computation, IEEE CEC 2005
Y2 - 2 September 2005 through 5 September 2005
ER -