Parameters estimation of hinging hyperplanes using median squared error criterion

  • Xiaolin HuangEmail author
  • Jun Xu
  • Shuning Wang
Regular Papers Control Theory


This paper considers parameter estimation for nonlinear model using median squared error (MSE) criterion, which is limited to linear model in the past. It is shown that applying MSE, the essence of estimating parameters for hinging hyperplanes (HH) and linear model are the same. Motivated by this fact, MSE estimation is discussed for HH. A local optimality condition is given and based on this condition, an algorithm using linear programming technique is proposed. Numerical experiments show the good performance of the proposed estimation strategy and algorithm.


Hinging hyperplane identification methods piecewise-linear robust estimation 


  1. [1]
    L. Breiman, “Hinging hyperplanes for regression, classification and function approximation,” IEEE Trans. on Information Theory, vol. 39, no. 3, pp. 999–1013, June 1993.MathSciNetzbMATHCrossRefGoogle Scholar
  2. [2]
    E. Bura and R. D. Cook, “Estimating the structural dimension of regressions via parametric inverse regression,” Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 63, no. 2, pp. 393–410, June 2001.MathSciNetzbMATHCrossRefGoogle Scholar
  3. [3]
    M. Camden, The Data Bundle, New Zealand Statistical Association, Wellington, New Zealand, 1989.Google Scholar
  4. [4]
    A. Cervantes, O. Agamennoni, and J. Figueroa, “A nonlinear model predictive control system based on Wiener piecewise linear models,” Journal of Process Control, vol. 13, no. 7, pp. 655–666, October 2003.CrossRefGoogle Scholar
  5. [5]
    B. Chakraborty and P. Chaudhuri, “On an optimization poblem in robust statistics,” Journal of Computational and Graphical Statistics, vol. 17, no. 3, pp. 683–702, September 2008.MathSciNetCrossRefGoogle Scholar
  6. [6]
    F. Chen and D. L. Qi, “Robust low complexity predictive control of constrained piecewise affine systems with bounded disturbances,” International Journal of Control, Automation and Systems, vol. 8, no. 2, pp. 439–444, April 2010.MathSciNetCrossRefGoogle Scholar
  7. [7]
    V. Cherkassky, D. Gehring, and F. Mulier, “Comparison of adaptive methods for function estimation from samples,” IEEE Trans. on Neural Networks, vol. 7, no. 4, pp. 969–984, August 1996.CrossRefGoogle Scholar
  8. [8]
    A. Chipperfield, P. Fleming, H. Pohlheim, and C. Fonseca, “Genetic algorithm toolbox user’s guide,” ACSE Research Report, no. 512, University of Sheffield, 1994.Google Scholar
  9. [9]
    L. O. Chua and S. M. Kang, “Section-wise piecewise-linear functions: canonical representation, properties, and applications,” Proc. of the IEEE, vol. 65, no. 6, pp. 915–929, June 1977.CrossRefGoogle Scholar
  10. [10]
    D. L. Donoho and P. J. Huber, “The notion of breakdown point,” A Festschrift for Erich L. Lehmann in Honor of His Sixty-fifth Birthday, pp. 157–184, February 1982.Google Scholar
  11. [11]
    S. Ernst, “Hinging hyperplane trees for approximation and identification,” Proc. of the 37th IEEE Conf. on Decision and Control, Tampa, Florida, USA, pp. 1266–1271, December 1998.Google Scholar
  12. [12]
    V. Hodge and J. Austin, “A survey of outlier detection methodologies,” Artificial Intelligence Review, vol. 22, no. 2, pp. 85–126, October 2004.zbMATHCrossRefGoogle Scholar
  13. [13]
    X. Huang, J. Xu, S. Wang, and C. Xu, “Minimization of the k-th maximum and its application on LMS regression and VaR optimization,” Submitted to Journal of Operations Research Society.Google Scholar
  14. [14]
    X. Huang, J. Xu, and S. Wang, “Operation optimization for centrifugal chiller plants using continuous piecewise linear programming,” Proc. IEEE International Conf. on Systems, Man, and Cybernetics, Istanbul, Turkey, pp. 1121–1126, October 2010.Google Scholar
  15. [15]
    P. Julián, A. Desages, and O. Agamennoni, “Highlevel canonical piecewise linear representation using a simplicial partition,” IEEE Trans. on Circuits and Systems-I: Fundamental Theory and Applications, vol. 46, no. 4, pp. 463–480, April 1999.zbMATHCrossRefGoogle Scholar
  16. [16]
    C. F. Olson, “An approximation algorithm for least median of squares regression,” Information Processing Letters, vol. 63, no. 5, pp. 237–241, September 1997.MathSciNetCrossRefGoogle Scholar
  17. [17]
    P. Pucar and J. Sjöberg, “On the hinge-finding algorithm for hingeing hyperplanes,” IEEE Trans. on Information Theory, vol. 44, no. 3, pp. 1310–1319, June 1998.zbMATHCrossRefGoogle Scholar
  18. [18]
    J. Roll, A. Bemporad, and L. Ljung, “Identification of piecewise affine system via mixed-integer programming,” Automatica, vol. 40, no. 1, 37–50, January 2004.MathSciNetzbMATHCrossRefGoogle Scholar
  19. [19]
    P. J. Rousseeuw, “Least median of squares regression,” Journal of the American Statistical Association, vol. 79, no. 388, pp. 871–880, December 1984.MathSciNetzbMATHCrossRefGoogle Scholar
  20. [20]
    P. J. Rousseeuw and M. Hubert, “Recent developments in PROGRESS,” Lecture Notes-Monograph Series, vol. 31, pp. 201–214, 1997.CrossRefGoogle Scholar
  21. [21]
    P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outlier Detection, Wiley-IEEE, 1987.Google Scholar
  22. [22]
    J. M. Steele and W. L. Steiger, “Algorithms and complexity for least median of squares regression,” Discrete Applied Mathematics, vol. 14, no. 1, pp. 93–100, May 1986.MathSciNetzbMATHCrossRefGoogle Scholar
  23. [23]
    A. J. Stromberg, “Computing the exact least median of squares estimate and stability diagnostics in multiple linear regression,” SIAM Journal on Scientific Computing, vol. 14, no. 6, pp. 1289–1299, December 1993.zbMATHCrossRefGoogle Scholar
  24. [24]
    J. M. Tarela and M. V. Martinez, “Region configurations for realizability of lattice piecewise-linear models,” Mathematical and Computer Modelling, vol. 30, no. 11–12, pp. 17–27, December 1999.MathSciNetzbMATHCrossRefGoogle Scholar
  25. [25]
    J. P. Vielma, S. Ahmed, and G. Nemhauser, “Mixed-integer models for nonseparable piecewise linear optimization: unifying framework and extension,” Operations Research, vol. 58, no. 2, pp. 303–315, March 2010.MathSciNetzbMATHCrossRefGoogle Scholar
  26. [26]
    S. Wang and X. Sun, “Generalization of hinging hyperplanes,” IEEE Trans. on Information Theory, vol. 51, no. 12, pp. 4425–4431, December 2005.CrossRefGoogle Scholar
  27. [27]
    C. Wen, S. Wang, X. Jin, and X. Ma, “Identification of dynamic systems using piecewise-affine basis function models,” Automatica, vol. 43, no. 10, pp. 1824–1831, October 2007.MathSciNetzbMATHCrossRefGoogle Scholar
  28. [28]
    J. Xu, X. Huang, and S. Wang, “Adaptive hinging hyperplanes and its applications in dynamic system identification,” Automatica, vol. 45, no. 10, pp. 2325–2332, October 2009.zbMATHCrossRefGoogle Scholar
  29. [29]
    J. Xu, X. Huang, and S. Wang, “Nonlinear model predictive control using adaptive hinging hyperplanes model,” Proc. of the 48th IEEE Conf. on Decision and Control, Shanghai, China, pp. 2598–2603, December 2009.Google Scholar
  30. [30]
    L. P. Zhu and L. X. Zhu, “A data-adaptive hybrid method for dimension reduction,” Journal of Nonparametric Statistics, vol. 21, no. 7, pp. 851–861, October 2009.MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Institute of Control, Robotics and Systems and The Korean Institute of Electrical Engineers and Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  1. 1.Department of AutomationTsinghua University and Tsinghua National Laboratory for Information Science and Technology (TNList)BeijingP. R. China

Personalised recommendations