The generalized complementarity problem includes the well-known nonlinear complementarity problem and linear complementarity problem as special cases.In this paper, based on a class of smoothing functions, a smoothing...The generalized complementarity problem includes the well-known nonlinear complementarity problem and linear complementarity problem as special cases.In this paper, based on a class of smoothing functions, a smoothing Newton-type algorithm is proposed for solving the generalized complementarity problem.Under suitable assumptions, the proposed algorithm is well-defined and global convergent.展开更多
By using a smoothing function,the P nonlinear complementarity problem(P NCP)can be reformulated as a parameterized smooth equation.A Newton method is proposed to solve this equation.The iteration sequence generated by...By using a smoothing function,the P nonlinear complementarity problem(P NCP)can be reformulated as a parameterized smooth equation.A Newton method is proposed to solve this equation.The iteration sequence generated by the proposed algorithm is bounded and this algorithm is proved to be globally convergent under an assumption that the P NCP has a nonempty solution set.This assumption is weaker than the ones used in most existing smoothing algorithms.In particular,the solution obtained by the proposed algorithm is shown to be a maximally complementary solution of the P NCP without any additional assumption.展开更多
2005年袁玉波等人用一个多项式函数作为光滑函数,提出了一个多项式光滑的支持向量机模型PSSVM(polynomial smooth support vector machine),使分类性能及效率得到了一定提高.2007年熊金志等人用插值函数的方法导出了一个递推公式,得到...2005年袁玉波等人用一个多项式函数作为光滑函数,提出了一个多项式光滑的支持向量机模型PSSVM(polynomial smooth support vector machine),使分类性能及效率得到了一定提高.2007年熊金志等人用插值函数的方法导出了一个递推公式,得到了一类新的光滑函数,解决了关于是否存在以及如何寻求性能更好的光滑函数的问题.然而,支持向量机是否存在其他多项式光滑模型,以及多项式光滑模型的一般形式是什么等问题依然存在.为此,将一类多项式函数作为新的光滑函数,使用光滑技术,提出了多项式光滑的支持向量机一般模型dPSSVM(dth-order polynomial smooth support vector machine).用数学归纳法证明了该一般模型的全局收敛性,并进行了数值实验.实验结果表明,当光滑阶数等于3时,一般模型的分类性能及效率为最好,并优于PSSVM模型;当光滑阶数大于3后,分类性能基本不变,效率会有所降低.成功解决了多项式光滑的支持向量机的一般形式问题.展开更多
针对目前光滑孪生支持向量回归机(smooth twin support vector regression,STSVR)中采用的Sigmoid光滑函数逼近精度不高,从而导致算法泛化能力不够理想的问题,引入一种具有更强逼近能力的光滑(chen-harker-kanzow-smale,CHKS)函数,采用C...针对目前光滑孪生支持向量回归机(smooth twin support vector regression,STSVR)中采用的Sigmoid光滑函数逼近精度不高,从而导致算法泛化能力不够理想的问题,引入一种具有更强逼近能力的光滑(chen-harker-kanzow-smale,CHKS)函数,采用CHKS函数逼近孪生支持向量回归机的不可微项,并用Newton-Armijo算法求解相应的模型,提出了光滑CHKS孪生支持向量回归机(smooth CHKS twin support vector regression,SCTSVR).不仅从理论上证明了SCTSVR具有严格凸,能满足任意阶光滑和全局收敛的性能,而且在人工数据集和UCI数据集上的实验表明了SCTSVR比STSVR具有更好的回归性能.展开更多
基金Supported by LIU Hui Centre for Applied Mathematics of Nankai University and Tianjin University
文摘The generalized complementarity problem includes the well-known nonlinear complementarity problem and linear complementarity problem as special cases.In this paper, based on a class of smoothing functions, a smoothing Newton-type algorithm is proposed for solving the generalized complementarity problem.Under suitable assumptions, the proposed algorithm is well-defined and global convergent.
基金Supported by China Postdoctoral Science Foundation(No.20060390660)Science and Technology Development Plan of Tianjin(No.06YFGZGX05600)+1 种基金Scientific Research Foundation of Liu Hui Center for Applied MathematicsNankai University-Tianjin University.
文摘By using a smoothing function,the P nonlinear complementarity problem(P NCP)can be reformulated as a parameterized smooth equation.A Newton method is proposed to solve this equation.The iteration sequence generated by the proposed algorithm is bounded and this algorithm is proved to be globally convergent under an assumption that the P NCP has a nonempty solution set.This assumption is weaker than the ones used in most existing smoothing algorithms.In particular,the solution obtained by the proposed algorithm is shown to be a maximally complementary solution of the P NCP without any additional assumption.
文摘2005年袁玉波等人用一个多项式函数作为光滑函数,提出了一个多项式光滑的支持向量机模型PSSVM(polynomial smooth support vector machine),使分类性能及效率得到了一定提高.2007年熊金志等人用插值函数的方法导出了一个递推公式,得到了一类新的光滑函数,解决了关于是否存在以及如何寻求性能更好的光滑函数的问题.然而,支持向量机是否存在其他多项式光滑模型,以及多项式光滑模型的一般形式是什么等问题依然存在.为此,将一类多项式函数作为新的光滑函数,使用光滑技术,提出了多项式光滑的支持向量机一般模型dPSSVM(dth-order polynomial smooth support vector machine).用数学归纳法证明了该一般模型的全局收敛性,并进行了数值实验.实验结果表明,当光滑阶数等于3时,一般模型的分类性能及效率为最好,并优于PSSVM模型;当光滑阶数大于3后,分类性能基本不变,效率会有所降低.成功解决了多项式光滑的支持向量机的一般形式问题.
文摘针对目前光滑孪生支持向量回归机(smooth twin support vector regression,STSVR)中采用的Sigmoid光滑函数逼近精度不高,从而导致算法泛化能力不够理想的问题,引入一种具有更强逼近能力的光滑(chen-harker-kanzow-smale,CHKS)函数,采用CHKS函数逼近孪生支持向量回归机的不可微项,并用Newton-Armijo算法求解相应的模型,提出了光滑CHKS孪生支持向量回归机(smooth CHKS twin support vector regression,SCTSVR).不仅从理论上证明了SCTSVR具有严格凸,能满足任意阶光滑和全局收敛的性能,而且在人工数据集和UCI数据集上的实验表明了SCTSVR比STSVR具有更好的回归性能.
