Minimize function in Tensorflow

16 Jan 2018

This post is to show how easy is to use tensorflow simply to minimize a function. Found here

import tensorflow as tf

x = tf.Variable(10.0, trainable=True)
f_x = 2 * x* x - 5 *x + 4

loss = f_x
opt = tf.train.GradientDescentOptimizer(0.1).minimize(f_x)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for i in range(100):
        print(sess.run([x,loss]))
        sess.run(opt)

x minimizes to the minimum at 1.25 and the los is the value at that point that is 0.875