Optimization by gradient boosting
From MaRDI portal
Publication:6289072
DOI10.1007/978-3-030-73249-3_2arXiv1707.05023MaRDI QIDQ6289072FDOQ6289072
Authors: Gérard Biau, Benoît Cadre 
Publication date: 17 July 2017
Abstract: Gradient boosting is a state-of-the-art prediction technique that sequentially produces a model in the form of linear combinations of simple predictors---typically decision trees---by solving an infinite-dimensional convex optimization problem. We provide in the present paper a thorough analysis of two widespread versions of gradient boosting, and introduce a general framework for studying these algorithms from the point of view of functional optimization. We prove their convergence as the number of iterations tends to infinity and highlight the importance of having a strongly convex risk functional to minimize. We also present a reasonable statistical context ensuring consistency properties of the boosting predictors as the sample size grows. In our approach, the optimization procedures are run forever (that is, without resorting to an early stopping strategy), and statistical regularization is basically achieved via an appropriate penalization of the loss and strong convexity arguments.
This page was built for publication: Optimization by gradient boosting
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6289072)
