To refer to this page use:
|Abstract:||We extend the theory of boosting for regression problems to the online learning setting. Generalizing from the batch setting for boosting, the notion of a weak learning algorithm is modeled as an online learning algorithm with linear loss functions that competes with a base class of regression functions, while a strong learning algorithm is an online learning algorithm with smooth convex loss functions that competes with a larger class of regression functions. Our main result is an online gradient boosting algorithm that converts a weak online learning algorithm into a strong one where the larger class of functions is the linear span of the base class. We also give a simpler boosting algorithm that converts a weak online learning algorithm into a strong one where the larger class of functions is the convex hull of the base class, and prove its optimality.|
|Electronic Publication Date:||2015|
|Citation:||Beygelzimer, A, Hazan, E, Kale, S, Luo, H. (2015). Online gradient boosting. 2015-January (2458 - 2466|
|Pages:||2458 - 2466|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||Advances in Neural Information Processing Systems|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.