IPBoost – Non-Convex Boosting via Integer Programming

02/11/2020

∙

by   Marc E. Pfetsch, et al.

∙

0

∙

share

Recently non-convex optimization approaches for solving machine learning problems have gained significant attention. In this paper we explore non-convex boosting in classification by means of integer programming and demonstrate real-world practicability of the approach while circumventing shortcomings of convex boosting approaches. We report results that are comparable to or better than the current state-of-the-art.