Sparse weighted voting classifier selection and its linear programming relaxations

Information Processing Letters

Volumn 112, Issue 12, 2012, Pages 481-486

  Goldberg, Noam ^a   Eckstein, Jonathan ^b  

^a ARGONNE NATIONAL LABORATORY   (United States)

^b the State University of New Jersey   (United States)

Author keywords

Computational complexity; Hardness of approximation; Integrality gap; Machine learning; Sparsity; Weighted voting classification

Indexed keywords

HARDNESS OF APPROXIMATION; INTEGRALITY GAPS; MACHINE-LEARNING; SPARSITY; WEIGHTED VOTING;

COMPUTATIONAL COMPLEXITY; INTEGER PROGRAMMING;

LINEAR PROGRAMMING;

EID: 84859523996     PISSN: 00200190     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ipl.2012.03.004     Document Type: Article

References (14)

1. N. Alon, and V. Vu Anti-hadamard matrices, coin weighing, threshold gates, and indecomposable hypergraphs J. Combin. Theory Ser. A 79 1997 133 160 (Pubitemid 127343390)
2. E. Amaldi, and V. Kann On the approximability of minimizing nonzero variables or unsatisfied relations in linear systems Theoret. Comput. Sci. 209 1998 237 260 (Pubitemid 128450440)
3. S. Arora, L. Babai, J. Stern, and Z. Sweedyk The hardness of approximate optima in lattices, codes, and systems of linear equations J. Comput. System Sci. 54 1997 317 331 (Pubitemid 127433376)
4. P. Bradley, and O. Mangasarian Feature selection via mathematical programming INFORMS J. Comput. 10 1998 209 217 (Pubitemid 128669128)
5. J. Brenner The Hadamard maximum determinant problem Amer. Math. Monthly 79 1972 626 630
6. A. Demiriz, K. Bennett, and J. Shawe-Taylor Linear programming boosting via column generation Mach. Learn. 46 2002 225 254 (Pubitemid 34129970)
7. I. Dinur, and S. Safra On the hardness of approximating label-cover Inform. Process. Lett. 89 2004 247 254
8. Y. Freund, and R. Schapire A decision-theoretic generalization of on-line learning and an application to boosting J. Comput. System Sci. 55 1997 119 139 (Pubitemid 127433398)
9. 0-relaxation penalties, in: Proceedings of the Twenty-Seventh International Conference on Machine Learning, 2010, pp. 383-390.
10. T. Graepel, R. Herbrich, B. Schölkopf, A. Smola, P. Bartlett, K.R. Müller, K. Obermayer, R. Williamson, Classification on proximity data with LP-machines, in: International Conference of Artificial Neural Networks, 1999, pp. 304-309. (Pubitemid 30519956)
11. J. Hastad On the size of weights for threshold gates SIAM J. Discrete Math. 7 1994 484 492
12. K.U. Höffgen, H. Simon, and K.V. Horn Robust trainability of single neurons J. Comput. System Sci. 50 1995 114 125
13. S. Muroga, I. Toda, and S. Takasu Theory of majority decision elements J. Franklin Inst. 271 1961 376 418
14. J. Weston, A. Elisseeff, B. Schölkopf, and M. Tipping Use of the zero norm with linear models and kernel methods J. Mach. Learn. Res. 3 2003 1439 1461