Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
StepSizeMatters/theorem4.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
98 lines (84 sloc)
3.34 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import matplotlib.pyplot as plt | |
import tensorflow as tf | |
tf.set_random_seed(962) #random seed for consistency | |
np.random.seed(962) | |
sess = tf.InteractiveSession() | |
def weight_variable(shape): | |
initial = tf.random_normal(shape, stddev=1.0) | |
return tf.Variable(initial) | |
def bias_vector(size): | |
initial = np.random.normal(0, 1.0, size) | |
return initial | |
#Start here | |
# intilize the tensorflow training set | |
x_dat = np.arange(0,1,0.001) | |
x_dat = np.expand_dims(x_dat,1) | |
N = len(x_dat) | |
d = 20 #number of nodes in the hidden layer | |
W = weight_variable([d,1]) | |
V = weight_variable([1,d]) | |
b = bias_vector([1,d]) | |
x = tf.placeholder(tf.float32, shape=[N,1]) | |
y_ = tf.placeholder(tf.float32, shape=[N,1]) | |
y = tf.matmul(tf.nn.relu(tf.matmul(x,V)-b),W) | |
train_loss = tf.reduce_sum(tf.square(y-y_)) | |
sess.run(tf.global_variables_initializer()) | |
y_dat = y.eval(feed_dict={x: x_dat}) | |
#calculate the bounds from the paper for the optimal solution | |
bound = 1/max([(abs(x_dat[i])*abs(y_dat[i])) for i in range(N)]) | |
bound = bound[0] | |
#Start here, can be set to bound | |
n = 10 #enter the number of datapoints | |
nstart = .117 #the higher of the step size | |
nend = .115 #the lower of the step size | |
r = 1000 #random iterations | |
#initilize the memory of the results | |
sums = [[0.0 for i in range(r)] for j in range(n)] | |
delta = [nstart+((i/(n-1))*(nend-nstart)) for i in range(n)] | |
conv = [[0 for i in range(r)] for j in range(n)] | |
conv2 = [[0 for i in range(r)] for j in range(n)] | |
#iterate over all the random initlizations | |
for rand_iter in range(r): | |
print(rand_iter) #Print the intialization to see how far the program has run | |
for step_iter in range(n): #iterate over all the step sizes | |
#Set the step size | |
delta_small = delta[step_iter] | |
#random weight initialization | |
train_step = tf.train.GradientDescentOptimizer(delta_small).minimize(train_loss) | |
sess.run(tf.global_variables_initializer()) | |
#Run the first time to get gradient | |
z3_dat = sess.run(y, feed_dict={x: x_dat}) | |
gradim1 = 0 | |
gradi = 1000000 #arbitratraily high | |
gradip1 = 10000000 #arbitratraily high | |
#iterate up to 1000 times | |
for g in range(1001): | |
train_step.run(feed_dict={x: x_dat, y_: y_dat}) | |
z4_dat = sess.run(y, feed_dict={x: x_dat}) #store the results | |
gradip1 = abs(z3_dat[0]-z4_dat[0])/delta_small # calculate the gradient | |
#Check if the gradient has converged | |
if(abs(abs(gradim1-gradi) - abs(gradi-gradip1)))<.001: | |
conv2[step_iter][rand_iter]= 1 | |
break | |
#update | |
gradim1 = gradi | |
gradi = gradip1 | |
z3_dat = z4_dat | |
#record error from intened solution | |
sums[step_iter][rand_iter] = sum([(y_dat[j]-z3_dat[j])**2 for j in range(len(z3_dat))]) | |
#If the function is within 100 of the intended solution, Layapunov stable convergence! | |
if (sums[step_iter][rand_iter] <1000): | |
conv[step_iter][rand_iter]= 1 | |
#percent gradient convergence | |
perc = [sum(i)/(r) for i in conv] | |
#percent solution convergence | |
perc2 = [sum(i)/(r) for i in conv2] | |
plt.plot(delta,perc2) | |
plt.xlabel("Step Size") | |
plt.ylabel("Convergence by Gradient Change Percentage") | |
plt.show() | |
plt.plot(delta,perc) | |
plt.xlabel("Step Size") | |
plt.ylabel("Convergence by Accuracy Percentage") | |
plt.show() | |