How to return parameters from all iterations of spicy.optimize.minimize

Question

I am using scipy.optimize.fmin to optimize the Rosenbrock function:

import scipy
import bumpy as np
def rosen(x):
    """The Rosenbrock function"""
    return sum(100.0*(x[1:]-x[:-1]**2.0)**2.0 + (1-x[:-1])**2.0)

x0 = np.array([1.3, 0.7, 0.8, 1.9, 1.2])
scipy.optimize.fmin(rosen, x0, full_output=True)

this returns a tuple for the solution (parameter that minimizes the function, the function minimum, number of iterations, number of function calls).

However I would like to be able to graph the values at each step. For example I would to plot the iteration number along the x-axis and the running minimum value along the y-axis.

score 3 · Accepted Answer · answered Oct 23 '15 at 14:59

fmin can take an optional callback function that gets called at each step, so you can just create a simple one that grabs the values at each step:

def save_step(k):
    global steps
    steps.append(k)

steps = []
scipy.optimize.fmin(rosen, x0, full_output=True, callback=save_step)
print np.array(steps)[:10]

Output:

[[ 1.339       0.721       0.824       1.71        1.236     ]
 [ 1.339       0.721       0.824       1.71        1.236     ]
 [ 1.339       0.721       0.824       1.71        1.236     ]
 [ 1.339       0.721       0.824       1.71        1.236     ]
 [ 1.2877696   0.7417984   0.8013696   1.587184    1.3580544 ]
 [ 1.28043136  0.76687744  0.88219136  1.3994944   1.29688704]
 [ 1.28043136  0.76687744  0.88219136  1.3994944   1.29688704]
 [ 1.28043136  0.76687744  0.88219136  1.3994944   1.29688704]
 [ 1.35935594  0.83266045  0.8240753   1.02414244  1.38852256]
 [ 1.30094767  0.80530982  0.85898166  1.0331386   1.45104273]]

How to return parameters from all iterations of spicy.optimize.minimize

1 Answers1