I am trying to run a regression model for a data set containing over 2000000 rows. I tried using linear regression and boosted decision tree regression without tuning model hyperparameter, I didn't get the expected accuracy. so I tried to use Tune model hyperparameter for the boosted decision tree, the model runs over 20 min. the decision forest also takes to0 long (even without tuning model hyperparameter). Is there any way to reduce the runtime without compromising the result accuracy too much?
will sampling affect the output (say I took 0.5 as sampling rate)?
The execution time on AzureML Studio depends on the pricing tier. The free version does one node execution at time while the standard pricing tier do the execute multiple execution at one time.