On the Convergence of Leveraging

Rätsch, Gunnar, Mika, Sebastian, Warmuth, Manfred K. K.

Neural Information Processing Systems 

We give an unified convergence analysis of ensemble learning methods including e.g. AdaBoost, Logistic Regression and the Least-Square- Boost algorithm for regression. These methods have in common that they iteratively call a base learning algorithm which returns hypotheses that are then linearly combined. We show that these methods are related to the Gauss-Southwell method known from numerical optimization and state non-asymptotical convergence results for all these methods. Our analysis includes -norm regularized cost functions leading to a clean and general way to regularize ensemble learning.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found