Linear Programming Boosting by Column and Row Generation

Abstract. We propose a new boosting algorithm based on a linear programming formulation. Our algorithm can take advantage of the sparsity of the solution of the underlying optimization problem. In preliminary experiments, our algorithm outperforms a state-of-the-art LP solver and LPBoost especially when the solution is given by a small set of relevant hypotheses and support vectors.

• Type: Conference
• Year: 2009
• Where: DIS
• Authors: Kohei Hatano, Eiji Takimoto
• Keywords: DIS 2009, Linear Programming Formulation, Optimization Problem, State-of-the-art Lp Solver, Theoretical Computer Science