For linear regression problems, MSE is a convex function and hence no matter where is the random initialization, Gradient Descent is guaranteed to approach arbitrarily close the global minimum (if we wait long enough and if the learning rate is not too high).
Taking you to the next exercise in seconds...
Want to create exercises like this yourself? Click here.
No hints are availble for this assesment
Answer is not availble for this assesment
Loading comments...