Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Lecture
Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture covers the theory of bagging, explaining how bagging always helps in improving the performance of machine learning models. The instructor discusses the assumptions behind bagging, the preparation for the theory, the claim that bagged output has smaller quadratic error than individual models, and provides a proof sketch. The lecture concludes with notes on the theory result, emphasizing the importance of uncorrelated data for the performance gain in bagging.