hey ,i am using this function to implement gradient descent but it returns only the theta value not the J_history value,Please help me in this situtation

function [theta,J_history] = gradientDescent(X, y, theta, alpha, num_iters)

% Initialize some useful values

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

J_history = zeros(num_iters, 1);

for iter = 1:num_iters

a1=(X*theta-y);

a2=(X*theta-y).*X;

theta(1)=theta(1)-alpha*sum(sum(a1))*(1/m);

theta(2)=theta(2)-alpha*sum(sum(a2))*(1/m);

% Save the cost J in every iteration

J_history(iter) = computeCost(X, y, theta);

end

end

Answer 1

[Rohit Kulkarni]

Hi Ashok,

Are you facing this same issue :

https://in.mathworks.com/matlabcentral/answers/787299-gradient-descent-fix

The answer to this may solve your problem.