Timeline for Gradient descent overshoot - why does it diverge?
Current License: CC BY-SA 3.0
12 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 2, 2020 at 12:56 | answer | added | user114966 | timeline score: 4 | |
| Aug 2, 2020 at 0:03 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Apr 4, 2020 at 0:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Dec 5, 2019 at 20:01 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Aug 8, 2019 at 8:52 | comment | added | Rodrigo de Azevedo | Take a look at this. | |
| Aug 7, 2019 at 20:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jul 8, 2019 at 19:09 | answer | added | gnasher729 | timeline score: 1 | |
| Jul 6, 2019 at 17:44 | comment | added | Prash Goel | I hope that this might be of some help: medium.com/@prash24goel/… | |
| Mar 16, 2016 at 17:46 | comment | added | Nicholas Mancuso | If $\alpha$ is too large it could continually overshoot and not converge. You can dynamically adjust the learning rate by using a simple line search algorithm that satisfies the Wolfe condition for each step. | |
| Mar 16, 2016 at 12:04 | history | edited | Raphael |
edited tags
|
|
| Mar 16, 2016 at 11:39 | review | First posts | |||
| Mar 16, 2016 at 16:24 | |||||
| Mar 16, 2016 at 11:36 | history | asked | user47979 | CC BY-SA 3.0 |