pytorch 寻找二元函数的最小值

定义函数

定义函数，用matplotlib画图

import numpy as np
import matplotlib.pyplot as plt


def himmelblau(x):
    return (x[0] ** 2 + x[1] - 11) ** 2 + (x[0] + x[1] ** 2 - 7) ** 2

x=np.arange(-6,6,0.1)
y=np.arange(-6,6,0.1)
print('x,y range:',x.shape,y.shape)
X,Y=np.meshgrid(x,y)
print('X Y maps:',X.shape,Y.shape)
Z=himmelblau([X,Y])

fig=plt.figure('himmelblau')
ax=fig.gca(projection='3d')
ax.plot_surface(X,Y,Z)
ax.view_init(60,-30)
ax.set_xlabel('x')
ax.set_ylabel('y')
plt.show()

用梯度下降法求解

1,确定优化目标（即要优化的参数，这也是要计算梯度的对象）

x=torch.tensor([0.,0.],requires_grad=True)

2,定义优化器，指定要优化的参数和学习率

optimizer=torch.optim.Adam([x],lr=1e-3)

3，循环迭代

for step in range(20000):
    pred = himmelblau(x)  # 得到预测值
    optimizer.zero_grad()  # 梯度清零
    pred.backward()  # 计算梯度大小，记录在参数的属性里
    optimizer.step()  # 根据之前定义的优化器更新梯度大小

    if step % 2000 == 0:
        print('step {}: x={}, f(x)={}'
              .format(step, x.tolist(), pred.item()))

完整代码：

import numpy as np
import matplotlib.pyplot as plt
import torch


def himmelblau(x):
    return (x[0] ** 2 + x[1] - 11) ** 2 + (x[0] + x[1] ** 2 - 7) ** 2


# plot
x=np.arange(-6,6,0.1)
y=np.arange(-6,6,0.1)
print('x,y range:',x.shape,y.shape)
X,Y=np.meshgrid(x,y)
print('X Y maps:',X.shape,Y.shape)
Z=himmelblau([X,Y])

fig=plt.figure('himmelblau')
ax=fig.gca(projection='3d')
ax.plot_surface(X,Y,Z)
ax.view_init(60,-30)
ax.set_xlabel('x')
ax.set_ylabel('y')
plt.show()

x = torch.tensor([0., 0.], requires_grad=True)
optimizer = torch.optim.Adam([x], lr=1e-3)
for step in range(20000):
    pred = himmelblau(x)  # 得到预测值
    optimizer.zero_grad()  # 梯度清零
    pred.backward()  # 计算梯度大小，记录在参数的属性里
    optimizer.step()  # 根据之前定义的优化器更新梯度大小

    if step % 2000 == 0:
        print('step {}: x={}, f(x)={}'
              .format(step, x.tolist(), pred.item()))