Sparse SVQR for Detecting Differently Expressed Genes
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Support vector quantile regression (SVQR) is capable of providing more complete description of the linear and nonlinear relationships among random variables. In this paper we propose the sparse SVQR whose objective function is composed of a weighted quadratic loss function and l1 norm penalty term. We use the iterative reweighted least squares (IRWLS) procedure to solve the objective problem of the proposed SVQR. Furthermore, we introduce the generalized approximate cross validation function to select the hyper-parameters which affect the performance of SVQR. Experimental results are then presented, which illustrate the performance of the sparse SVQR using IRWLS procedure.
Abstract
Support vector quantile regression (SVQR) is capable of providing more complete description of the linear and nonlinear relationships among random variables. In this paper we propose the sparse SVQR whose objective function is composed of a weighted quadratic loss function and l1 norm penalty term. We use the iterative reweighted least squares (IRWLS) procedure to solve the objective problem of the proposed SVQR. Furthermore, we introduce the generalized approximate cross validation function to select the hyper-parameters which affect the performance of SVQR. Experimental results are then presented, which illustrate the performance of the sparse SVQR using IRWLS procedure.
참고문헌 (21)
- Koenker R, "Regression quantile", Econometrica, 46, pp.33~50 (1978)
- Koenker R, "Quantile regression", J Econ Perspect, 40, pp.122~142 (2001)
- Yu K, "Quantile regression : applications and current research area", Statistician, 52, pp.331~350 (2003)
- Koenker R, "Quantile regression" (2005), Cambridge University Press
- Shim J, "Support vector censored quantile regression under random censoring", Comput Stat Data An, 53, pp.912~917 (2009)
- Vapnik VN, "The nature of statistical learning theory" (1995), Springer
- Vapnik VN, "Statistical learning theory" (1998), John Wiley
- Smola A, "On a kernel-based method for pattern recognition, regression, approximation and operator inversion", Algorithmica, 22, pp.211~231 (1998)
- Tipping ME, "Sparse Bayesian learning and the relevance vector machine", J Mach Learn Res, 1, pp.211~244 (2001)
- Hwang C, "A simple quantile regression via support vector machine", Lect Notes Comput Sc, 3610, pp.512~520 (2005)
- Takeuchi I, "Nonparametric quantile estimation", J Mach Learn Res, 7, pp.1231~1264 (2006)
- Mercer J, "Functions of positive and negative type and their connection with theory of integral equations", Philos T Roy Soc A, 209, pp.415~446 (1909)
- Kuhn HW, "Nonlinear programming", Proceedings of 2nd Berkeley Symposium, pp.481~492 (1951)
- Yuan M, "GACV for Quantile smoothing splines", Comput Stat Data An, 50, pp.813~829 (2006)
- Li Y, "Quantile regression in reproducing kernel Hilbert spaces", J Am Stat Assoc, 102, pp.255~268 (2007)
- Williams PM, "Bayesian regularization and pruning using a Laplace prior", Neural Comput, 7, pp.117~143 (1995)
- Krishnapuram B, "Sparse multinomial logistic regression : fast algorithms and generalization bounds", IEEE T Pattern Anal, 27, pp.957~968 (2005)
- Craven P, "Smoothing noisy data with spline functions : estimating the correct degree of smoothing by the method of generalized cross-validation", Numer Math, 31, pp.377~403 (1979)
- Sohn I, "Support vector machine quantile regression for detecting differently expressed genes in microarray analysis", Method Inform Med, 47, pp.459~467 (2008)
- Balagurunathan Y, "Simulation of cDNA microarrays via a parameterized random signal model", J Biomed Opt, 7, pp.507~523 (2002)
- Cawley GC, "Heteroscedastic kernel ridge regression", Neurocomputing, 57, pp.105~124 (2004)