Coursera 机器学习 Week6 编程作业: Regularized Linear Regression and Bias/Variance

此次作业需要我们实现正则线性化，并在此基础上解决训练过程中出现的过拟合和欠拟合问题。

1 Regularized Linear Regression

这一部分需要我们通过线性正则化来实现预测大坝的出水量。

1.1 Visualizing the dataset

此次给出的训练数据中$X$只有一维，我们会在后面的练习中多项式话它。
训练数据的图像如下：

1.2 Regularized linear regression cost function

正则化线性回归的代价函数如下：
$$J(\theta )=\frac{1}{2m}(\sum _{i=1}^m(h_{\theta }(x^{(i)})-y^{(i)}{)}^2)+\frac{\lambda }{2m}(\sum _{j=1}^n{\theta }_j^2)$$
我们需要在linearRegCostFunction.m中完成代价函数的求解。
代码如下：

linearRegCostFunction.m

m = length(y); % number of training examples

% You need to return the following variables correctly 
J = 0;

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost and gradient of regularized linear 
%               regression for a particular choice of theta.
%
%               You should set J to the cost and grad to the gradient.
%
% cost function compute
h = X*theta;
J = (1/(2*m))*((h-y)'*(h-y))+((lambda/(2*m))*(theta'*theta-theta(1)^2));

1.3 Regularized linear regression gradient

此部分需要我们完成正则化线性回归中的梯度求解
梯度求解公式如下：
$$\frac{\partial J(\theta )}{\partial {\theta }_0}=\frac{1}{m}\sum _{i=1}^m(h_{\theta }(x^{(i)})-y^{(i)})x_j^{(i)}j=0$$
$$\frac{\partial J(\theta )}{\partial {\theta }_j}=\frac{1}{m}\sum _{i=1}^m(h_{\theta }(x^{(i)})-y^{(i)})x_j^{(i)}+\frac{\lambda }{m}{\theta }_{j}j>0$$
我们在linearRegCostFunction.m完成梯度的计算

linearRegCostFunction.m

% compute grad
grad = 1/m*(X'*(h-y))+lambda/m*theta;
grad(1) = grad(1) - lambda/m*theta(1);

完整的linearRegCostFunction.m代码如下：

function [J, grad] = linearRegCostFunction(X, y, theta, lambda)
%LINEARREGCOSTFUNCTION Compute cost and gradient for regularized linear 
%regression with multiple variables
%   [J, grad] = LINEARREGCOSTFUNCTION(X, y, theta, lambda) computes the 
%   cost of using theta as the parameter for linear regression to fit the 
%   data points in X and y. Returns the cost in J and the gradient in grad

% Initialize some useful values
m = length(y); % number of training examples

% You need to return the following variables correctly 
J = 0;
grad = zeros(size(theta));

% ====================== YOUR CODE HERE ======================
% Instructions: Compute the cost and gradient of regularized linear 
%               regression for a particular choice of theta.
%
%               You should set J to the cost and grad to the gradient.
%
h = X*theta;
J = (1/(2*m))*((h-y)'*(h-y))+((lambda/(2*m))*(theta'*theta-theta(1)^2));
grad = 1/m*(X'*(h-y))+lambda/m*theta;
grad(1) = grad(1) - lambda/m*theta(1);

% =========================================================================

grad = grad(:);

end

1.4 Fitting linear regression

完成了代价函数和梯度的计算后就可以通过fmincg函数通过计算出$minJ(\theta )$下的 $\theta$了。
在这一部分，我们设$\lambda$为0，因为正则化不会对二维数据产生多么大的帮助，可以忽略不计。
下面我们画出了最佳拟合的图像。

可以看出我们预测的$h_{\theta }(x)$没有很好的拟合给出的训练数据，这说明这个问题不仅仅是能用一次函数能解决的，我们需要对特征值进行多项式化。在下面的练习中我们需要实现特征值的多项式化。

2 Bias-variance

在此部分练习中，我们将在学习曲线上绘制训练和测试错误，以判断偏差-方差问题。

2.1 Learning curves

这一部分我们将会绘制学习曲线，学习曲线对我们的学习算法调试非常有用。
学习曲线的$X$轴表示的是训练数据的大小，$Y$轴表示的是误差。
通过绘制出train data 和 cross validation 各自的$J(\theta )$曲线来判断是否存在过拟合或欠拟合问题。
$J_{train}(\theta )$和$J_{cv}(\theta )$的求解公式如下:

$$J_{train}(\theta )=\frac{1}{2m}(\sum _{i=1}^m(h_{\theta }(x^{(i)})-y^{(i)}{)}^2)$$
$$J_{cv}(\theta )=\frac{1}{2m_{cv}}(\sum _{i=1}^{m_{cv}}(h_{\theta }(x_{cv}^{(i)})-y_{cv}^{(i)}{)}^2)$$
我们需要对$J_{train}(\theta )$和$J_{cv}(\theta )$进行求解
此部分需要我们在learningCurve.m完成。
代码如下：

learningCurve.m

function [error_train, error_val] = ...
    learningCurve(X, y, Xval, yval, lambda)
%LEARNINGCURVE Generates the train and cross validation set errors needed 
%to plot a learning curve
%   [error_train, error_val] = ...
%       LEARNINGCURVE(X, y, Xval, yval, lambda) returns the train and
%       cross validation set errors for a learning curve. In particular, 
%       it returns two vectors of the same length - error_train and 
%       error_val. Then, error_train(i) contains the training error for
%       i examples (and similarly for error_val(i)).
%
%   In this function, you will compute the train and test errors for
%   dataset sizes from 1 up to m. In practice, when working with larger
%   datasets, you might want to do this in larger intervals.
%

% Number of training examples
m = size(X, 1);

% You need to return these values correctly
error_train = zeros(m, 1);
error_val   = zeros(m, 1);

% ====================== YOUR CODE HERE ======================
% Instructions: Fill in this function to return training errors in 
%               error_train and the cross validation errors in error_val. 
%               i.e., error_train(i) and 
%               error_val(i) should give you the errors
%               obtained after training on i examples.
%
% Note: You should evaluate the training error on the first i training
%       examples (i.e., X(1:i, :) and y(1:i)).
%
%       For the cross-validation error, you should instead evaluate on
%       the _entire_ cross validation set (Xval and yval).
%
% Note: If you are using your cost function (linearRegCostFunction)
%       to compute the training and cross validation error, you should 
%       call the function with the lambda argument set to 0. 
%       Do note that you will still need to use lambda when running
%       the training to obtain the theta parameters.
%
% Hint: You can loop over the examples with the following:
%
%       for i = 1:m
%           % Compute train/cross validation errors using training examples 
%           % X(1:i, :) and y(1:i), storing the result in 
%           % error_train(i) and error_val(i)
%           ....
%           
%       end
%

% ---------------------- Sample Solution ----------------------

for i=1:m
  theta=trainLinearReg(X(1:i,:),y(1:i,:),lambda);
  [error_train(i),grad] = linearRegCostFunction(X(1:i,:),y(1:i,:),theta,0);
  [error_val(i),grad] = linearRegCostFunction(Xval,yval,theta,0);
endfor

% -------------------------------------------------------------

% =========================================================================

end

可以看出随着训练数据的增加,训练数据和交叉验证数据的误差都很高，这反映了模型具有高偏差问题(欠拟合)。我们可以通过多项式化来解决。

3 Polynomial regression

在这一部分中，我们需要给我们的训练来加上更多的特征。
我们可以通过增加特征值幂的方式来增加特征值。
我们可以令$h_{\theta }(x)$等于如下形式：
$$h_{\theta }(x)={\theta }_0+{\theta }_{1}x+{\theta }_2{x}^2+{\theta }_3{x}^3+...+{\theta }_p{x}^p$$
我们需要在polyFeatures.m中完成增添多项式特征。
代码如下：

polyFeatures.m

function [X_poly] = polyFeatures(X, p)
%POLYFEATURES Maps X (1D vector) into the p-th power
%   [X_poly] = POLYFEATURES(X, p) takes a data matrix X (size m x 1) and
%   maps each example into its polynomial features where
%   X_poly(i, :) = [X(i) X(i).^2 X(i).^3 ...  X(i).^p];
%

% You need to return the following variables correctly.
X_poly = zeros(numel(X), p);

% ====================== YOUR CODE HERE ======================
% Instructions: Given a vector X, return a matrix X_poly where the p-th 
%               column of X contains the values of X to the p-th power.
%
% 
for i=1:p
  X_poly(:,i) = X.^i;
endfor

% =========================================================================

end

3.1 Learning Polynomial Regression

在完成以上任务之后，我们需要对我们的训练数据进行特征规范化，然后我们再次训练数据，令$\lambda =0$得到的图像如下：

然后我们再将学习曲线画出：

发现存在过拟合问题，所以我们需要调整合适的$\lambda$来解决过拟合问题。

3.3 Selecting λ using a cross validation set

此部分需要我们选出合适的$\lambda$来解决过拟合问题。我们通过设置不同的$\lambda$来求出不同的$\theta$然后分别求出$J_{train}$和$J_{cv}$，然后绘制图像来观察最合适的$\lambda$。
我们需要完成validationCurve.m中的求解$J_{train}$和$J_{cv}$功能。
代码如下：

validationCurve.m

function [lambda_vec, error_train, error_val] = ...
    validationCurve(X, y, Xval, yval)
%VALIDATIONCURVE Generate the train and validation errors needed to
%plot a validation curve that we can use to select lambda
%   [lambda_vec, error_train, error_val] = ...
%       VALIDATIONCURVE(X, y, Xval, yval) returns the train
%       and validation errors (in error_train, error_val)
%       for different values of lambda. You are given the training set (X,
%       y) and validation set (Xval, yval).
%

% Selected values of lambda (you should not change this)
lambda_vec = [0 0.001 0.003 0.01 0.03 0.1 0.3 1 3 10]';

% You need to return these variables correctly.
error_train = zeros(length(lambda_vec), 1);
error_val = zeros(length(lambda_vec), 1);

% ====================== YOUR CODE HERE ======================
% Instructions: Fill in this function to return training errors in 
%               error_train and the validation errors in error_val. The 
%               vector lambda_vec contains the different lambda parameters 
%               to use for each calculation of the errors, i.e, 
%               error_train(i), and error_val(i) should give 
%               you the errors obtained after training with 
%               lambda = lambda_vec(i)
%
% Note: You can loop over lambda_vec with the following:
%
%       for i = 1:length(lambda_vec)
%           lambda = lambda_vec(i);
%           % Compute train / val errors when training linear 
%           % regression with regularization parameter lambda
%           % You should store the result in error_train(i)
%           % and error_val(i)
%           ....
%           
%       end
%
%
for i=1:length(lambda_vec)
  lambda = lambda_vec(i);
  theta = trainLinearReg(X,y,lambda);
  %theta_v = trainLinearReg(Xval,yval,lambda);
  [error_train(i),grad] = linearRegCostFunction(X,y,theta,0);
  [error_val(i),grad] = linearRegCostFunction(Xval,yval,theta,0);
endfor

% =========================================================================

end

注意 这次里的$J_{train}$和$J_{cv}$与前面的$J_{train}$和$J_{cv}$求法是一样的，都不带正则化的式子。
绘制的图像如下：

从图像上可以看出$\lambda$的最佳值为3。

3.4 Optional (ungraded) exercise: Computing test set error

此部分是选做部分，我们需要在$\lambda =3$的前提下计算$J_{test}$,跟前面的算法是一样的，求出$\theta$然后带入求解$J_{test}$的式子，$J_{test}$同样不需要正则化求解。