The randomized Kaczmarz method with mismatched adjoint

This paper investigates the randomized version of the Kaczmarz method to solve linear systems in the case where the adjoint of the system matrix is not exact—a situation we refer to as “mismatched adjoint”. We show that the method may still converge both in the over- and underdetermined consistent case under appropriate conditions, and we calculate the expected asymptotic rate of linear convergence. Moreover, we analyze the inconsistent case and obtain results for the method with mismatched adjoint as for the standard method. Finally, we derive a method to compute optimized probabilities for the choice of the rows and illustrate our findings with numerical examples.     

A convergent criss-cross method

Our paper presents a new Criss-Cross method for solving linear programming problems. Starting from a neither primal nor dual feasible solution, we reach an optimal solution in finite number of steps if it exists. If there is no optimal solution, then we show that there is not primal feasible or dual feasible solution, We prove the finiteness of this procedure. Our procedure is not the same as the primal or dual simplex method if we have a primal or dual feasible solution, so we have constructed a quite new procedure for solving linear programming problems.     

PP multivariate random weighting method

According to the Projection Pursuit (PP) method and the random weighting method, we propose a PP random weighting method, and set up the asymptotic distribution theory and strong limit theorem of PP random weighting empirical process. Applying this method, we obtain two kinds of goodness-of-fit test for a multivariate distribution function, i.e., we get the random weighting approximations of PP Kolmogorov Smirnov statistics (PPKS) and PP Smirnov Cramér Von Mises statistics (PPSC), we prove that the asymptotic distribution of PPKS and PPSC are the same as those of their respective random weighting approximations.Supported by the National Natural Science Foundation of China.     

Modified descent-projection method for solving variational inequalities

In this paper, we propose a modified descent-projection method for solving variational inequalities. The method makes use of a descent direction to produce the new iterate and can be viewed as an improvement of the descent-projection method by using a new step size. Under certain conditions, the global convergence of the proposed method is proved. In order to demonstrate the efficiency of the proposed method, we provide numerical results for a traffic equilibrium problems.     

An efficient method for fractional nonlinear differential equations by quasi‐Newton's method and simplified reproducing kernel method

An efficient method for nonlinear fractional differential equations is proposed in this paper. This method consists of 2 steps. First, we linearize the nonlinear operator equation by quasi‐Newton's method, which is based on Fréchet derivative. Then we solve the linear fractional differential equations by the simplified reproducing kernel method. The convergence of the quasi‐Newton's method is discussed for the general nonlinear case as well. Finally, some numerical examples are presented to illustrate accuracy, efficiency, and simplicity of the method.     

A dual method to the collocation method

In this article we consider methods which are related to the collocation method by interchanging the test and the trial spaces. Error estimates are derived. As a by-product we obtain some extensions to the known convergence results for the collocation method.     

Confidence interval estimation by a joint pivot method

The Birnbaum–Saunders distribution is widely used in fields such as survival analysis. In this paper, we use a new method to construct confidence intervals for the shape parameter of the Birnbaum–Saunders distribution and find it superior to some existing methods. Our method can be called the “joint pivot method” as we obtain the confidence interval by uniting two pivots. Furthermore, we find that the joint pivot method can also be used to solve the Behrens–Fisher problem. Simulation studies show that the joint pivot method is comparable with some commonly practiced ones. Finally, we analyse two real data sets to illustrate the proposed procedure.     

The reduction method,II

In part I of this paper focusing on a further development of the well-known algorithms for deriving theorems of the method of Lyapunov vector functions, we suggested the reduction method as a logical technique for formulating hypotheses. This part illustrates its implementation in qualitative analysis of the various properties of dynamical systems represented as systems of motions, differential equations, and automata models with different depths of delays.     

A two-step extragradient method for variational inequalities

In this paper we consider an extragradient method for solving variational inequalities and related problems. On each iteration this method makes two trial steps along the gradient, and the value of the gradient at the second point is used at the first point as the iteration direction. We prove the convergence of this method in a general case. For problems with a bilinear functional we prove the geometric convergence rate.     

Alternating direction method for bi-quadratic programming

Bi-quadratic programming (Bi-QP for short) was studied systematically in Ling et al. (SIAM J. Optim. 20:1286–1320, 2009) due to its various applications in engineering as well as optimization. Several approximation methods were given in the same paper since it is NP-hard. In this paper, we introduce a quadratic SDP relaxation of Bi-QP and discuss the approximation ratio of the method. In particular, by exploiting the favorite structure of the quadratic SDP relaxation, we propose an alternating direction method for solving such a problem and show that the method is globally convergent without any assumption. Some preliminary numerical results are reported which show the effectiveness of the method proposed in this paper.     

A steepest descent method for vector optimization

In this work we propose a Cauchy-like method for solving smooth unconstrained vector optimization problems. When the partial order under consideration is the one induced by the nonnegative orthant, we regain the steepest descent method for multicriteria optimization recently proposed by Fliege and Svaiter. We prove that every accumulation point of the generated sequence satisfies a certain first-order necessary condition for optimality, which extends to the vector case the well known “gradient equal zero” condition for real-valued minimization. Finally, under some reasonable additional hypotheses, we prove (global) convergence to a weak unconstrained minimizer.As a by-product, we show that the problem of finding a weak constrained minimizer can be viewed as a particular case of the so-called Abstract Equilibrium problem.     

Continuous-discontinuous finite element method for convection-diffusion problems with characteristic layers

We study convergence properties of a numerical method for convection-diffusion problems with characteristic layers on a layer-adapted mesh. The method couples standard Galerkin with an h-version of the nonsymmetric discontinuous Galerkin finite element method with bilinear elements. In an associated norm, we derive the error estimate as well as the supercloseness result that are uniform in the perturbation parameter. Applying a post-processing operator for the discontinuous Galerkin method, we construct a new numerical solution with enhanced convergence properties.     

On the Secant method for solving nonsmooth equations

In this study we are concerned with the problem of approximating a locally unique solution of an operator equation in Banach space using the Secant method. The differentiability of the operator involved is not assumed. Using a flexible point-based approximation, we provide a local as well as a semilocal convergence analysis for the Secant method. Our results are justified by numerical examples that cannot be handled with earlier works.     

A hybrid method for sound-hard obstacle reconstruction

We are interested in solving the inverse problem of acoustic wave scattering to reconstruct the position and the shape of sound-hard obstacles from a given incident field and the corresponding far field pattern of the scattered field. The method we suggest is an extension of the hybrid method for the reconstruction of sound-soft cracks as presented in [R. Kress, P. Serranho, A hybrid method for two-dimensional crack reconstruction, Inverse Problems 21 (2005) 773–784] to the case of sound-hard obstacles. The designation of the method is justified by the fact that it can be interpreted as a hybrid between a regularized Newton method applied to a nonlinear operator equation with the operator that maps the unknown boundary onto the solution of the direct scattering problem and a decomposition method in the spirit of the potential method as described in [A. Kirsch, R. Kress, On an integral equation of the first kind in inverse acoustic scattering, in: Cannon, Hornung (Eds.), Inverse Problems, ISNM, vol. 77, 1986, pp. 93–102. Since the method does not require a forward solver for each Newton step its computational costs are reduced. By some numerical examples we illustrate the feasibility of the method.     

A modified Broyden-like method for nonlinear complementarity problems

In this paper, we give a modified Broyden-like method for nonlinear complementarity problems, where we consider the smoothing parameter as an independent variable in the smoothing equation and adopt a modified nonmonotone step-length decision. We also analyze the global and local convergence of the modified method. Numerical experiments are also shown.     

Digital contracts-driven method for pricing complex derivatives

In this paper, we propose a hybrid method of nonparametric and parametric methods, that is a digital contracts-driven (DCD) method, for pricing various complex options. Differing from general nonparametric data-driven methods, in which usually the observed data are used as training data directly, in the DCD method the European-style digital contracts of the underlying assets are used as basic inputs for a learning network. The digital contracts calculated from the observed data based upon the parametric method are used as hints in the learning process, and then enable the DCD method to have superior pricing accuracy to the common data-driven method in practical applications. Some Monte Carlo simulation experiments are performed and the results demonstrate that the proposed hybrid method not only has the advantages of generality and superior accuracy as the nonparametric method, but also the robust property to financial data with noise as the parametric method.     

Preconditioned AHSS iteration method for singular saddle point problems

In this paper, for solving the singular saddle point problems, we present a new preconditioned accelerated Hermitian and skew-Hermitian splitting (AHSS) iteration method. The semi-convergence of this method and the eigenvalue distribution of the preconditioned iteration matrix are studied. In addition, we prove that all eigenvalues of the iteration matrix are clustered for any positive iteration parameters α and β. Numerical experiments illustrate the theoretical results and examine the numerical effectiveness of the AHSS iteration method served either as a preconditioner or as a solver.     

求解稀疏逻辑回归问题的嵌套BB算法的分裂增广拉格朗日算法

逻辑回归是经典的分类方法,广泛应用于数据挖掘、机器学习和计算机视觉.现研究带有程。模约束的逻辑回归问题.这类问题广泛用于分类问题中的特征提取,且一般是NP-难的.为了求解这类问题,提出了嵌套BB(Barzilai and Borwein)算法的分裂增广拉格朗日算法(SALM-BB).该算法在迭代中交替地求解一个无约束凸优化问题和一个带程。模约束的二次优化问题.然后借助BB算法求解无约束凸优化问题.通过简单的等价变形直接得到带程。模约束二次优化问题的精确解,并且给出了算法的收敛性定理.最后通过数值实验来测试SALM-BB算法对稀疏逻辑回归问题的计算精确性.数据来源包括真实的UCI数据和模拟数据.数值实验表明,相对于一阶算法SLEP,SALM-BB能够得到更低的平均逻辑损失和错分率.     

Epsilon-proximal decomposition method

We propose a modification of the proximal decomposition method investigated by Spingarn [30] and Mahey et al. [19] for minimizing a convex function on a subspace. For the method to be favorable from a computational point of view, particular importance is the introduction of approximations in the proximal step. First, we couple decomposition on the graph of the epsilon-subdifferential mapping and cutting plane approximations to get an algorithmic pattern that falls in the general framework of Rockafellar inexact proximal-point algorithms [26]. Recently, Solodov and Svaiter [27] proposed a new proximal point-like algorithm that uses improved error criteria and an enlargement of the maximal monotone operator defining the problem. We combine their idea with bundle mecanism to devise an inexact proximal decomposition method with error condition which is not hard to satisfy in practice. Then, we present some applications favorable to our development. First, we give a new regularized version of Benders decomposition method in convex programming called the proximal convex Benders decomposition algorithm. Second, we derive a new algorithm for nonlinear multicommodity flow problems among which the message routing problem in telecommunications data networks.     

Solving semi-infinite programs by smoothing projected gradient method

In this paper, we study a semi-infinite programming (SIP) problem with a convex set constraint. Using the value function of the lower level problem, we reformulate SIP problem as a nonsmooth optimization problem. Using the theory of nonsmooth Lagrange multiplier rules and Danskin’s theorem, we present constraint qualifications and necessary optimality conditions. We propose a new numerical method for solving the problem. The novelty of our numerical method is to use the integral entropy function to approximate the value function and then solve SIP by the smoothing projected gradient method. Moreover we study the relationships between the approximating problems and the original SIP problem. We derive error bounds between the integral entropy function and the value function, and between locally optimal solutions of the smoothing problem and those for the original problem. Using certain second order sufficient conditions, we derive some estimates for locally optimal solutions of problem. Numerical experiments show that the algorithm is efficient for solving SIP.