Solve a non-negative least-squares problem with the LARS algorithm (see nonnegativeLeastSquares()) or the Goldfarb-Idnani algorithm (see quadraticProgramming())
Usage: example_nnlsq
(no parameters - example data are defined in nnlsq.cxx)
#include <iostream>
#include <vigra/matrix.hxx>
#include <vigra/regression.hxx>
#include <vigra/quadprog.hxx>
double A_data[] = {
1, -3, 2,
-3, 10, -5,
2, -5, 6
};
double b_data[] = {
27,
-78,
64
};
int main()
{
std::cout << "solution LARS: ";
std::cout << x(
k,0) <<
", ";
std::cout << "\n";
empty,
x = 0;
std::cout << "solution Goldfarb-Idnani: ";
std::cout << x(
k,0) <<
", ";
std::cout << "\n";
}
Class for a single RGB value.
Definition rgbvalue.hxx:128
Linear algebra functions.
Definition eigensystem.hxx:50
void transpose(const MultiArrayView< 2, T, C1 > &v, MultiArrayView< 2, T, C2 > &r)
Definition matrix.hxx:965
unsigned int nonnegativeLeastSquares(...)
unsigned int quadraticProgramming(...)