Timeline for Batch gradient descent versus stochastic gradient descent
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 23, 2020 at 5:42 | comment | added | Xiao-Feng Li | @Media You are right. I've removed the last paragraph. Thanks. | |
| Dec 23, 2020 at 5:32 | history | edited | Xiao-Feng Li | CC BY-SA 4.0 |
deleted 198 characters in body
|
| Dec 19, 2020 at 2:53 | comment | added | Green Falcon | Why have you said virtually in * finally in one epoch, you are virtually computing the mean of the gradients based on all the given samples.*? Don't you think this claim is wrong due to updating the weights at each step? | |
| Mar 31, 2018 at 3:18 | comment | added | Xiao-Feng Li | @horaceT Thanks for your comment. Since the point you mentioned has been described by Jason_L_Bens above with details, I did not bother to repeat but referring his answer in the last third paragraph, with due respect. To gradient descent optimization problem, non-convex is reflected by the local minima including saddle point (see the last third paragraph); and for the sake of description, my answer describes SGD as minibatch but with a batch size of 1 (see the third paragraph). | |
| Mar 31, 2018 at 0:52 | comment | added | horaceT | For convex optimization problems, what you said is fine. But to use gradient methods on non-convex functions, you missed a very critical reason that SGD is better than batch GD. See my response datascience.stackexchange.com/questions/16807/… | |
| Mar 30, 2018 at 22:18 | history | answered | Xiao-Feng Li | CC BY-SA 3.0 |