This topic contains 0 replies, has 1 voice, and was last updated by jose123456789 2 months, 1 week ago.
Viewing 1 post (of 1 total)
Viewing 1 post (of 1 total)
You must be logged in to reply to this topic.
Home 2015 › Forums › Numerical Method › Optimization › Differential Evolution
Tagged: genetic algo, portfolio optimization
This topic contains 0 replies, has 1 voice, and was last updated by jose123456789 2 months, 1 week ago.
Hello guys : I am testing the differential evolution class:
I have a very large basket (a qquadratic problem) that I want to optmize subject to contraints:
equal, greater and less than.
When I run the optimization using other methods (no diffwerential evoution) I get convergence but
it can take 30 minutes to run for 1400 tickers.
I want to give Genetic Algo a try to find optimal value opf weights.
basically I want to know how to set up the problem correctly, please point me in the right direction.
what do I have to correct i the definition below?
——————————————————————————————–
QPProblem problem = new QPProblem(F, equal, greater, less);
DEOptim solver = new DEOptim(new DEOptim.NewCellFactory() {
@Override
public DEOptimCellFactory newCellFactory() {
return new IntegralConstrainedCellFactory(new Rand1Bin(0.5, 0.5, uniform), new IntegralConstrainedCellFactory.AllIntegers());
}
}, uniform, 0.00001, 400000, 100);
IterativeSolution soln = solver.solve(problem);
————————————————————————–
I wonder if you could be so kind to point me out in the right direction.
How can I define the problem in suach a way that that the minumum is a vector of real numbers
respecting the inequalitiers (equal, less and greater)
Do u have more examples illustrating the differential evolution class in algoquant? (besides the integer optimization of cross over strategy)
Thank you,
ja
You must be logged in to reply to this topic.
Recent Comments