My intuition is that GD would converge faster if you update the parameters one by one because the second update will be more “accurate” if it considers the first parameter update - the first parameter update will slightly change the shape of the curve for the second parameter. Of course, it’s compu…

Why is it important to update both parameters at the same time?

rmwkwok June 22, 2022, 1:39pm 11

Here’s the deviation for the case of one w, but the same logic applies to more.

1 Like

Interpreting coefficients of scaled features

Topic		Replies	Views
Simultaneous update of parameters w & b in Gradient Descent in Multiple Linear Regression Supervised ML: Regression and Classification week-2	5	300	May 30, 2024
Course 1 week 2 gradient descent Neural Networks and Deep Learning	2	577	September 24, 2021
Why we need GD algorithm if we can still optimise parameters of the model? Calculus for Machine Learning and Data Science week-2	7	370	August 24, 2023
Multiple Linear Regression Supervised ML: Regression and Classification week-2	2	605	July 1, 2022
Gradient Descent Query Advanced Learning Algorithms week-3	1	347	September 16, 2023