What is the difference between the fit functions of regression model and the train regression models in regression learner app?

I am a begginer in Matlab machine learning toolbox.

I applied both methods, regression learner app and fit functions for my dataset.

For example, from regression learner app, I selected ensemble boosted tree. The results were similar to the fitrensemble fuction when I used 'OptimizeHyperparameters','auto'.

Now, I have this question in my mind, what is the difference between these two methods, if we can get the same results?

Is there any way to improve the optimization of the results?

Appreciate for any comments.

Answer 1

[Dheeraj Singh]

As per the documentation of fitrensemble it returns the trained regression ensemble model object (Mdl) that contains the results of boosting 100 regression trees using LSBoost .

Ensemble boosted tree also uses Least-squares boosting (LSBoost).

This may be the reason for getting similar results for both.You can also change the method used in fitrensembleand then compare your results.