1

Possible Duplicate:
Fast gradient-descent implementation in a C++ library?

I'm looking to run a gradient descent optimization to minimize the cost of an instantiation of variables. My program is very computationally expensive, so I'm looking for a popular library with a fast implementation of GD. What is the recommended library/reference?

Community
  • 1
  • 1
  • 2
    The GSL (GNU Scientific Library) http://www.gnu.org/software/gsl/ isn't bad, I've used it frequently before. Alternatively, you could call the R optimization routines from C++, but that's more work. – jbowman Jul 16 '12 at 23:56
  • If you're down to worrying about such costs, you're probably better off searching for a new method, such as Newton's method, conjugate gradients, etc. What works will depend on your specific problem. – Chris A. Jul 21 '12 at 02:04

0 Answers0