Timeline for Does gradient descent always converge to an optimum?
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 16, 2017 at 23:36 | vote | accept | wit221 | ||
| Nov 16, 2017 at 20:30 | comment | added | Green Falcon | @RicardoCruz yes, I do agree sir | |
| Nov 16, 2017 at 17:38 | comment | added | Ricardo Cruz | Exactly. These problems always pop up in theory, but rarely in actual practice. With so many dimensions, this isn't an issue. You'll have a local minima in one variable, but not in another. Furthermore, mini-batch or stochastic gradient descent ensures also help avoiding any local minima. | |
| Nov 9, 2017 at 18:07 | history | edited | Green Falcon | CC BY-SA 3.0 |
added 65 characters in body
|
| Nov 9, 2017 at 17:56 | history | answered | Green Falcon | CC BY-SA 3.0 |