Skip to yearly menu bar Skip to main content


Poster

IPBoost – Non-Convex Boosting via Integer Programming

Marc Pfetsch · Sebastian Pokutta

Keywords: [ Combinatorial Optimization ] [ Non-convex Optimization ] [ Supervised Learning ] [ Boosting / Ensemble Methods ]


Abstract:

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 circumvent- ing shortcomings of convex boosting approaches. We report results that are comparable to or better than the current state-of-the-art.

Chat is not available.