Timeline for What is the trade-off between batch size and number of iterations to train a neural network?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 23, 2021 at 23:13 | comment | added | Cloud Cho | Sorry for confusion, my question was "Is the optimal solution in your answer same with (so called) the global minimum"? | |
| Aug 23, 2021 at 21:27 | comment | added | Lars Ericson | My subsequent intuition is that larger batch sizes will help prevent overfitting. | |
| Aug 20, 2021 at 17:17 | comment | added | Cloud Cho | thanks for the post with snippet. Is the optimal solution is the same with the global minimum? If yes, have your experimented gradient direction varying by bath size? | |
| Jul 4, 2018 at 21:44 | history | answered | Lars Ericson | CC BY-SA 4.0 |