Gradient Descent algorithms converge to a local minimum, and if the function is convex, they converge to a __________ minimum.

41.What does gradient descent help in finding?  A. Local maximum of a function  B. Local minimum of a function  C. Global maximum of function  D. Global minimum of function

Gradient Descent is an optimization algorithm used for ______

Which of the following statements about Gradient Descent are true? (Select all that apply)Group of answer choicesLearning rate is a crucial hyperparameter in its performance.It requires calculation of gradients for the entire dataset.It can be very slow when the dataset is very large.It is guaranteed to find the global minimum for non-convex functions.

Explain the role of the following factors in reaching global minima with a gradient descent algorithm for linear regression.a. Epochsb. Learning ratec. Parametersd. Bias and Variance

Consider Newton's method applied to the minimisation problemminxf(x).min𝑥𝑓(𝑥).Which of the following statements is true regarding the convergence of Newton's method.Question 1Answera.If f𝑓 is convex and has positive definite Hessian for all x𝑥 and Newton's method converges, then it converges to a global minimiser of f𝑓.b.Newton's method always converges to a global minimiser of f𝑓. c.If f𝑓 is convex and has positive definite Hessian for all x𝑥 then Newton's method always converges.d.Newton's method always requires damping in order to converge to a global minimiser of f𝑓.