Sparse weighted voting classifier selection and its linear programming relaxations

DOI10.1016/j.ipl.2012.03.004zbMath1243.68239MaRDI QIDQ436579

Jonathan Eckstein, Noam Goldberg

Publication date: 25 July 2012

Published in: Information Processing Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ipl.2012.03.004

zbMATH Keywords

computational complexity; machine learning; sparsity; hardness of approximation; integrality gap; weighted voting classification

Mathematics Subject Classification ID

90C90: Applications of mathematical programming

90C11: Mixed integer programming

68T05: Learning and adaptive systems in artificial intelligence

90C05: Linear programming

68Q17: Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.)

Uses Software

• AdaBoost.MH