Data sets for the paper "Mining Markov Network Surrogates for Value-Added Optimisation"
by Alexander E.I. Brownlee sbr@cs.stir.ac.uk www.cs.stir.ac.uk/~sbr
Presented in the SAEOpt Workshop at GECCO 2016
DOI:10.1145/2908961.2931711

Files:
10runs-cost-biuni-1000-sel400.txt
10runs-cost-uni-400-sel140.txt
10runs-energy-biuni-1000-sel400.txt
10runs-energy-uni-400-sel140.txt
These are the aggregated model coefficients for the four MFMs mentione in the paper (cost/energy univariate/univariate+bivariate).
Columns are: coeffNumber mean stdDev

biuni-cost-predicts.txt
biuni-energy-predicts.txt
uni-cost-predicts.txt
uni-energy-predicts.txt
These are the predicted and true fitness values for the test solutions used to compute r^2 for the four MFMs mentione in the paper (cost/energy univariate/univariate+bivariate).

coefficients.xlsx
These are the model coefficients for the ten repeat runs of each model.
Each tab's rows are:
rowNumber
120 columns for univariate alphas
240 columns for bivariate alphas if applicable
1 colum for constant