Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revision | |||
| data_mining:crossvalidation [2018/05/10 12:10] – phreazer | data_mining:crossvalidation [2018/05/10 12:30] (current) – [Mismatched train/test distribution] phreazer | ||
|---|---|---|---|
| Line 10: | Line 10: | ||
| ===== Mismatched train/test distribution ===== | ===== Mismatched train/test distribution ===== | ||
| - | * Should have same distribution | + | * Should have same distribution, but sometimes training set needs more data which comes from different distribution |
| + | * Then dev/test set should come from same distribution | ||
| + | |||
| + | Sometimes there is no test set, so you don't have a **unbiased** estimation (might overfit to dev set). | ||