Convergence of Gradient Descent

Thala · July 10, 2022, 6:47am

In the convergence of gradient descent lecture in week 2, Andrew speaks about convergence to global minima. I am confused since in earlier lectures he had said that we will find local minima and since at local minima the derivative term is zero, the parameters wont change afterwards.

can anybody explain it if i have misunderstood any part?

TMosh · July 10, 2022, 7:36am

Normally we prefer to use convex cost functions. That means there is only one minimum, and there aren’t any local minima that can trap the convergence.

Topic		Replies	Views
Query regarding local and global minima Supervised ML: Regression and Classification week-1	2	530	July 1, 2022
Cost function - How can we make sure that we end up in the global minimum and not one of the local minima Supervised ML: Regression and Classification week-2	2	755	December 3, 2022
C1_W1_Gradient-Descent Supervised ML: Regression and Classification week-1	3	568	July 28, 2022
Gradient descent C1_W1 Supervised ML: Regression and Classification week-1	2	513	July 31, 2022
Doubt regarding a potential limitation of gradient descent Supervised ML: Regression and Classification week-1	5	100	June 10, 2024

Convergence of Gradient Descent

Related topics