Timeline for Is it possible to use stochastic gradient descent at the beginning, then switch to batch gradient descent with only a few training examples?
Current License: CC BY-SA 4.0
8 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Nov 6, 2021 at 17:00 | comment | added | nbro | Ok, can you please edit your post to clarify that? | |
Nov 6, 2021 at 16:08 | vote | accept | Robo | ||
Nov 6, 2021 at 16:05 | comment | added | Robo | I meant that, I heard that in stochastic gradient descent, if the cost function is not actually at the global optimum but is somewhere close by, it won't matter a lot because you still get almost similar results. | |
Nov 3, 2021 at 12:17 | comment | added | nbro | I don't understand this sentence "I know that a model with a cost function that's a bit away from the lowest value for the cost function performs well in stochastic gradient descent". What do you mean by "a model with a cost function that's a bit away from the lowest value for the cost function". There's probably a typo there, which you should fix. | |
Nov 3, 2021 at 12:16 | history | edited | nbro | CC BY-SA 4.0 |
added 1 character in body; edited tags; edited title
|
Nov 3, 2021 at 10:03 | answer | added | spiridon_the_sun_rotator | timeline score: 2 | |
S Nov 3, 2021 at 7:41 | review | First questions | |||
Nov 4, 2021 at 5:34 | |||||
S Nov 3, 2021 at 7:41 | history | asked | Robo | CC BY-SA 4.0 |