import org.apache.commons.math.optimization.direct.NelderMead; //导入依赖的package包/类
@Test
public void testRosenbrock()
  throws FunctionEvaluationException, ConvergenceException {

  Rosenbrock rosenbrock = new Rosenbrock();
  NelderMead underlying = new NelderMead();
  underlying.setStartConfiguration(new double[][] {
                                       { -1.2,  1.0 }, { 0.9, 1.2 } , {  3.5, -2.3 }
                                   });
  JDKRandomGenerator g = new JDKRandomGenerator();
  g.setSeed(16069223052l);
  RandomVectorGenerator generator =
      new UncorrelatedRandomVectorGenerator(2, new GaussianRandomGenerator(g));
  MultiStartMultivariateRealOptimizer optimizer =
      new MultiStartMultivariateRealOptimizer(underlying, 10, generator);
  optimizer.setConvergenceChecker(new SimpleScalarValueChecker(-1, 1.0e-3));
  optimizer.setMaxIterations(100);
  RealPointValuePair optimum =
      optimizer.optimize(rosenbrock, GoalType.MINIMIZE, new double[] { -1.2, 1.0 });

  assertEquals(rosenbrock.getCount(), optimizer.getEvaluations());
  assertTrue(optimizer.getEvaluations() > 20);
  assertTrue(optimizer.getEvaluations() < 250);
  assertTrue(optimum.getValue() < 8.0e-4);

}
 

import org.apache.commons.math.optimization.direct.NelderMead; //导入依赖的package包/类
@Override
		public double detect(final double[] vec) {
			double[] t = {this.mean.detect(vec)};
			MultivariateRealFunction func = new MultivariateRealFunction() {
				@Override
				public double value(double[] x) throws FunctionEvaluationException {
					ObjectDoublePair<double[]> ind = indicator(vec,x[0]);
					double sumd = MatlibMatrixUtils.sum(D);
					double k = ind.second / sumd;
					double b = k / (1-k);
					double[][] y = new double[1][vec.length];
					for (int i = 0; i < vec.length; i++) {
						y[0][i] = ind.first[i] + 1 - b * (1 - ind.first[i]);
					}
					SparseMatrix dmw = MatlibMatrixUtils.minusInplace(D, W);
					Vector yv = Vector.wrap(y[0]);
					double nom = new DenseMatrix(y).mult(dmw.transposeMultiply(yv)).get(0); // y' * ( (D-W) * y)
					double denom = new DenseMatrix(y).mult(D.transposeMultiply(yv)).get(0);
					return nom/denom;
				}

			}; 
			
//			
			RealPointValuePair ret;
			try {
				NelderMead nelderMead = new NelderMead();
				nelderMead.setConvergenceChecker(new SimpleRealPointChecker(0.0001, -1));
				ret = nelderMead.optimize(func, GoalType.MINIMIZE, t);
				return ret.getPoint()[0];
			} catch (Exception e) {
				e.printStackTrace();
				System.err.println("Reverting to mean");
			}
			return t[0];
		}