Predict objective function run times at a set of points



time = predictObjectiveEvaluationTime(results,XTable) returns estimated objective evaluation times at the points in XTable.


collapse all

This example shows how to estimate the objective function evaluation time in an optimized Bayesian model of SVM classification.

Create an optimized SVM model. For details of this model, see Optimize a Cross-Validated SVM Classifier Using bayesopt.

rng default
grnpop = mvnrnd([1,0],eye(2),10);
redpop = mvnrnd([0,1],eye(2),10);
redpts = zeros(100,2);
grnpts = redpts;
for i = 1:100
    grnpts(i,:) = mvnrnd(grnpop(randi(10),:),eye(2)*0.02);
    redpts(i,:) = mvnrnd(redpop(randi(10),:),eye(2)*0.02);
cdata = [grnpts;redpts];
grp = ones(200,1);
grp(101:200) = -1;
c = cvpartition(200,'KFold',10);
sigma = optimizableVariable('sigma',[1e-5,1e5],'Transform','log');
box = optimizableVariable('box',[1e-5,1e5],'Transform','log');
minfn = @(z)kfoldLoss(fitcsvm(cdata,grp,'CVPartition',c,...
results = bayesopt(minfn,[sigma,box],'IsObjectiveDeterministic',true,...

Predict the evaluation time for various points.

sigma = logspace(-5,5,11)';
box = 1e5*ones(size(sigma));
XTable = table(sigma,box);
time = predictObjectiveEvaluationTime(results,XTable);
ans=11×3 table
    sigma      box      time  
    ______    _____    _______

     1e-05    1e+05    0.29193
    0.0001    1e+05    0.30467
     0.001    1e+05    0.28848
      0.01    1e+05    0.25716
       0.1    1e+05    0.24492
         1    1e+05    0.47912
        10    1e+05     1.8356
       100    1e+05    0.79565
      1000    1e+05    0.24908
     10000    1e+05    0.21283
     1e+05    1e+05    0.20923

Input Arguments

collapse all

Bayesian optimization results, specified as a BayesianOptimization object.

Prediction points, specified as a table with D columns, where D is the number of variables in the problem. The function performs its predictions on these points.

Data Types: table

Output Arguments

collapse all

Estimated objective evaluation times, returned as an N-by-1 vector, where N is the number of rows of XTable. The estimated values are the means of the posterior distribution of the Gaussian process model of the evaluation times of the objective function.

Introduced in R2016b