If we consider two conditions:
- Number of data is huge
- Number of data is low
For what condition does boosting or bagging overfit more compared to the other one?
Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.Sign up to join this community
I read your question as: 'Is boosting more vulnerable to overfitting than bagging?'
Firstly, you need to understand that bagging decreases variance, while boosting decreases bias.
Also, to be noted that under-fitting means that the model has low variance and high bias and vice versa for overfitting.
So, boosting is more vulnerable to overfitting than bagging.