python - 增加线性回归的成本

Question

出于训练目的，我在 python 中实现了线性回归。问题是成本在增加而不是减少。对于数据，我使用机翼自噪声数据集。资料可查here

我按如下方式导入数据:

import pandas as pd

def features():

    features = pd.read_csv("data/airfoil_self_noise/airfoil_self_noise.dat.txt", sep="\t", header=None)

    X = features.iloc[:, 0:5]
    Y = features.iloc[:, 5]

    return X.values, Y.values.reshape(Y.shape[0], 1)

我的线性回归代码如下:

import numpy as np
import random

class linearRegression():

    def __init__(self, learning_rate=0.01, max_iter=20):
        """
        Initialize the hyperparameters of the linear regression.

        :param learning_rate: the learning rate
        :param max_iter: the max numer of iteration to perform
        """

        self.lr = learning_rate
        self.max_iter = max_iter
        self.m = None
        self.weights = None
        self.bias = None

    def fit(self, X, Y):
        """
        Run gradient descent algorithm

        :param X: the inputs
        :param Y: the outputs
        :return:
        """

        self.m = X.shape[0]
        self.weights = np.random.normal(0, 0.1, (X.shape[1], 1))
        self.bias = random.normalvariate(0, 0.1)

        for iter in range(0, self.max_iter):

            A = self.__forward(X)
            dw, db = self.__backward(A, X, Y)

            J = (1/(2 * self.m)) * np.sum(np.power((A - Y), 2))

            print("at iteration %s cost is %s" % (iter, J))

            self.weights = self.weights - self.lr * dw
            self.bias = self.bias - self.lr * db

    def predict(self, X):
        """
        Make prediction on the inputs

        :param X: the inputs
        :return:
        """

        Y_pred = self.__forward(X)

        return Y_pred

    def __forward(self, X):
        """
        Compute the linear function on the inputs

        :param X: the inputs
        :return:
            A: the activation
        """

        A = np.dot(X, self.weights) + self.bias

        return A

    def __backward(self, A, X, Y):
        """

        :param A: the activation
        :param X: the inputs
        :param Y: the outputs
        :return:
            dw: the gradient for the weights
            db: the gradient for the bias
        """

        dw = (1 / self.m) * np.dot(X.T, (A - Y))
        db = (1 / self.m) * np.sum(A - Y)

        return dw, db

然后我实例化 linearRegression 类如下:

X, Y = features()
model = linearRegression()
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=42)
model.fit(X_train, y_train)

我试图找出成本增加的原因，但到目前为止我无法找出原因。如果有人能指出我正确的方向，我们将不胜感激。

Answer 1

通常，如果您选择较大的学习率，您可能会遇到类似的问题。我已尝试检查您的代码，我的观察结果是:

• 您的成本函数 J 似乎没问题。
• 但在你的反向函数中，你似乎从你的猜测中减去你的实际结果。通过这样做，您可能会得到负权重，并且由于您从权重和梯度中减去学习率和速率的乘积，您最终会得到增加的成本函数结果