If a gradient points towards a max or a min what stops gradient descent from maximizing error instead of minimizing it?
Is it the nature of the update step that makes this process one way?
$\begingroup$
$\endgroup$
1
asked Apr 22, 2019 at 16:53
-
4$\begingroup$ Possible duplicate of How can change in cost function be positive? see also stats.stackexchange.com/questions/367397/… $\endgroup$– Sycorax ♦Commented Apr 22, 2019 at 17:19
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
In gradient decent, we are following the negative gradient direction, where the objective function will decrease instead of increase.
answered Apr 22, 2019 at 16:58