参考梯度下降和随机梯度下降
以f(x) = x2为例
import matplotlib.pyplot as plt
import numpy as np
import torch
import math
def gd(eta,iter):
x = 10
results = []
for i in range(iter):
x -= eta * 2 * x # f(x) = x * x的导数为f'(x) = 2 * x
results.append(x)
return results
res = gd(0.2,iter = 10)
print(res)
# 绘制出自变量x的迭代轨迹
def show_trace(res):
n = max(abs(min(res)), abs(max(res)), 10)
f_line = np.arange(-n, n, 0.1)
plt.plot(f_line, [x * x for x in f_line])
plt.plot(res, [x * x for x in res], '-o')
plt.xlabel('x')
plt.ylabel('f(x)')
plt.figure(1)
show_trace(res)
# 学习率
res = gd(0.05,10) #学习率过小迭代10次不能达到最优解
plt.figure(2)
show_trace(res)
res = gd(0.05,100) #迭代100次达到最优解,100是我自己随意设的,只是100次肯定与最优解误差不大
plt.figure(3)
print(res,'\n')
show_trace(res)
res = gd(1.1,10) #学习率过大
plt.figure(4)
print(res)
show_trace(res)
# 多维梯度下降------------------------------------------------------
def train_2d(trainer):
x1, x2, s1, s2 = -5, -2, 0, 0 # s1和s2是自变量状态,本章后续几节会使用
results = [(x1, x2)]
for i in range(20):
x1, x2, s1, s2 = trainer(x1, x2, s1, s2)
results.append((x1, x2))
print('epoch %d, x1 %f, x2 %f' % (i + 1, x1, x2))
return results
def show_trace_2d(f, results):
plt.plot(*zip(*results), '-o', color='#ff7f0e')
x1, x2 = np.meshgrid(np.arange(-5.5, 1.0, 0.1), np.arange(-3.0, 1.0, 0.1))
plt.contour(x1, x2, f(x1, x2), colors='#1f77b4')
plt.xlabel('x1')
plt.ylabel('x2')
def f_2d(x1, x2): # 目标函数
return x1 ** 2 + 2 * x2 ** 2
def gd_2d(x1, x2, s1, s2):
return (x1 - eta * 2 * x1, x2 - eta * 4 * x2, 0, 0)
eta = 0.1
plt.subplot(3,2,5)
show_trace_2d(f_2d, train_2d(gd_2d))
# 随机梯度下降-----------------------------
# 通过在梯度中添加均值为0的随机噪声来模拟随机梯度下降,以此来比较它与梯度下降的区别
def sgd_2d(x1, x2, s1, s2):
return (x1 - eta * (2 * x1 + np.random.normal(0.1)),
x2 - eta * (4 * x2 + np.random.normal(0.1)), 0, 0)
plt.subplot(3,2,6)
show_trace_2d(f_2d, train_2d(sgd_2d))
#当训练数据集的样本较多时,梯度下降每次迭代的计算开销较大,因而随机梯度下降通常更受青睐。```