时变挥发率条件下求解Steiner树蚁群优化算法的收敛性

蚁群优化算法是最近提出的求解复杂组合优化问题的启发式算法.在蚁群优化算法中,信息素的更新规则直接影响着算法性能,固定挥发率条件下,虽然也能得到求解Steinei树蚁群优化算法的收敛性结果,但算法的探优能力差,易于陷入局部最优.本文在设计求解最小Steiner树蚁群优化算法时,采用了动态更新信息索挥发率的方法,并给出了时变挥发率条件下算法的收敛性证明.具体的,在时变挥发率条件下,当迭代次数充分大时,该算法能以概率1找到最优解.另外,在动态更新信息素下界的条件下,也能得到类似的收敛性结果.     

等式约束优化非单调信赖域算法

设计了一个新的求解等式约束优化问题的非单调信赖域算法.该算法不需要罚函数也无需滤子.在每次迭代过程中只需求解满足下降条件的拟法向步及切向步.新算法产生的迭代步比滤子方法更易接受,计算量比单调算法小.在一般条件下,算法具有全局收敛性.     

基于有效约束识别技术的一个SSLE算法及其收敛性分析

基于一个有效约束识别技术, 给出了具有不等式约束的非线性最优化问题的一个可行SSLE算法. 为获得搜索方向算法的每步迭代只需解两个或三个具有相同系数矩阵的线性方程组. 在一定的条件下, 算法全局收敛到问题的一个KKT点. 没有严格互补条件, 在比强二阶充分条件弱的条件下算法具有超线性收敛速度.     

仿射变换内点信赖域方法求解变分不等式问题

本文研究了求解非线性约束变分不等式问题(VIP)的一个新的算法.利用KKT条件的非光滑方程形式,得到了与VIP等价的简单约束优化问题.提出了求解VIP的一类结合回代线搜索技巧的仿射变换内点信赖域算法.在较弱的条件下证明了算法具有整体收敛性,进一步在某些正则条件下,证明了算法具有超线性收敛速度.     

一种求解不等式约束优化问题的光滑化算法

利用光滑函数建立了不等式约束优化问题KT条件的一个扰动方程组,提出了一个新的内点型算法.该算法在有限步终止时当前迭代点即为优化问题的一个精确稳定点.在一定条件下算法具有全局收敛性,数值试验表明该算法是有效的.     

一个充分下降的改进HS共轭梯度法

共轭梯度法是求解大规模无约束优化问题最有效的方法之一.对HS共轭梯度法参数公式进行改进,得到了一个新公式,并以新公式建立一个算法框架.在不依赖于任何线搜索条件下,证明了由算法框架产生的迭代方向均满足充分下降条件,且在标准Wolfe线搜索条件下证明了算法的全局收敛性.最后,对新算法进行数值测试,结果表明所改进的方法是有效的.     

不等式约束优化的一个超线性收敛FSSLE算法

本文针对不等式约束优化问题,提出了一个可行序列线性方程组(FSSLE)算法.该算法每次迭代只需求解四个具有相同系数矩阵的线性方程组,因而计算量较小.在没有假设算法产生的聚点是孤立点和近似乘子列有界的条件下,证明了算法具有全局收敛性.在一般条件下,证明了算法具有超线性收敛性.     

一类新的具有充分下降条件和强收敛性的共轭梯度法

本文研究了求解无约束优化问题的WYL共轭梯度法.利用修正迭代格式,得到了算法在每步迭代能产生不依赖于搜索条件的充分下降方向.同时,在原算法中关于Wolfe条件中参数去掉的情况下,获得了本文算法是强收敛的.数值实验说明本文算法可以有效求解测试问题.     

凸约束伪单调方程组的无导数投影算法

基于HS共轭梯度法的结构,本文在弱假设条件下建立了一种求解凸约束伪单调方程组问题的迭代投影算法.该算法不需要利用方程组的任何梯度或Jacobian矩阵信息,因此它适合求解大规模问题.算法在每一次迭代中都能产生充分下降方向,且不依赖于任何线搜索条件.特别是,我们在不需要假设方程组满足Lipschitz条件下建立了算法的全局收敛性和R-线收敛速度.数值结果表明,该算法对于给定的大规模方程组问题是稳定和有效的.     

解不等式约束优化的新的序列线性方程组方法

提出一种新的序列线性方程组(SSLE)算法解非线性不等式约束优化问题.在算法的每步迭代,子问题只需解四个简化的有相同的系数矩阵的线性方程组.证明算法是可行的,并且不需假定聚点的孤立性、严格互补条件和积极约束函数的梯度的线性独立性得到算法的全局收敛性.在一定条件下,证明算法的超线性收敛率.     

NEW HYBRID CONJUGATE GRADIENT METHOD AS A CONVEX COMBINATION OF LS AND FR METHODS

In this paper, we present a new hybrid conjugate gradient algorithm for unconstrained optimization. This method is a convex combination of Liu-Storey conjugate gradient method and Fletcher-Reeves conjugate gradient method. We also prove that the search direction of any hybrid conjugate gradient method, which is a convex combination of two conjugate gradient methods, satisfies the famous D-L conjugacy condition and in the same time accords with the Newton direction with the suitable condition. Furthermore, this property doesn't depend on any line search. Next, we also prove that, moduling the value of the parameter t,the Newton direction condition is equivalent to Dai-Liao conjugacy condition.The strong Wolfe line search conditions are used.The global convergence of this new method is proved.Numerical comparisons show that the present hybrid conjugate gradient algorithm is the efficient one.     

Numerical integration and the constant strain condition

The finite element method is a very popular method for numerically solving boundary value problems. A sufficient condition for the convergence of this method is the so-called constant strain condition. In this paper we present a proof, using elementary linear algebra, that numerical integration does not affect the ability of an element to satisfy the constant strain condition.     

一种改进的共轭梯度法及全局收敛性

本文在DY共轭梯度法的基础上对解决无约束最优化问题提出一种改进的共轭梯度法.该方法在Wolfe线搜索下能够保证充分下降性,并在目标函数可微的条件下,证明了算法的全局收敛性.大量数值试验表明,该方法是很有效的.     

Spectral Optimization Methods for the Time Fractional Diffusion Inverse Problem

An inverse problem of reconstructing the initial condition for a time fractional diffusion equation is investigated. On the basis of the optimal control framework, the uniqueness and first order necessary optimality condition of the minimizer for the objective functional are established, and a time-space spectral method is proposed to numerically solve the resulting minimization problem. The contribution of the paper is threefold: 1) a priori error estimate for the spectral approximation is derived; 2) a conjugate gradient optimization algorithm is designed to efficiently solve the inverse problem; 3) some numerical experiments are carried out to show that the proposed method is capable to find out the optimal initial condition, and that the convergence rate of the method is exponential if the optimal initial condition is smooth.     

Log-Sigmoid nonlinear Lagrange method for nonlinear optimization problems over second-order cones

This paper analyzes the rate of local convergence of the Log-Sigmoid nonlinear Lagrange method for nonconvex nonlinear second-order cone programming. Under the componentwise strict complementarity condition, the constraint nondegeneracy condition and the second-order sufficient condition, we show that the sequence of iteration points generated by the proposed method locally converges to a local solution when the penalty parameter is less than a threshold and the error bound of solution is proportional to the penalty parameter. Finally, we report numerical results to show the efficiency of the method.     

Strong Predictor-Corrector Approximation for Stochastic Delay Differential Equations

This paper presents a strong predictor-corrector method for the numerical solution of stochastic delay differential equations (SDDEs) of Itô-type. The method is proved to be mean-square convergent of order min{$1/2, \hat{p}$} under the Lipschitz condition and the linear growth condition, where $\hat{p}$ is the exponent of Hölder condition of the initial function. Stability criteria for this type of method are derived. It is shown that for certain choices of the flexible parameter $p$ the derived method can have a better stability property than more commonly used numerical methods. That is, for some $p$, the asymptotic MS-stability bound of the method will be much larger than that of the Euler-Maruyama method. Numerical results are reported confirming convergence properties and comparing stability properties of methods with different parameters $p$. Finally, the vectorised simulation is discussed and it is shown that this implementation is much more efficient.     

强单调对称非线性方程组的BFGS算法

提出一种求解强单调非线性方程组的BFGS算法,该算法的一个明显优点是Bκ的条件数比Li-Fukushima^[3]提出的GNBFGS中Bκ的条件数小得多。且该算法是一种无需计算导数的下降算法。在一定的条件下,证明了算法的全局收敛性和超线性收敛性。最后进行数值试验,结果表明,本文算法具有较好的数值结果。而且验证了本文所提出的算法中Bκ的条件数要比GNBFGS算法的条件数小得多。     

Mean‐square stability of the backward Euler–Maruyama method for neutral stochastic delay differential equations with jumps

This paper is mainly considered whether the mean‐square stability of neutral stochastic delay differential equations (NSDDEs) with jumps is shared with that of the backward Euler–Maruyama method. Under the one‐sided Lipschitz condition and the linear growth condition, the trivial solution of NSDDEs with jumps is proved to be mean‐square stable by using the functional comparison principle and the Barbalat's lemma. It is shown that the backward Euler–Maruyama method can reproduce the mean‐square stability of the trivial solution under the same conditions. The implicit backward Euler–Maruyama method shows better characteristic than the explicit Euler–Maruyama method for the reason that it works without the linear growth condition on the drift coefficient. Compared with some existing results, our results do not need to add extra condition on the neutral part. The conclusions can be applied to NSDDEs and SDDEs with jumps. The effectiveness of the theoretical results is illustrated by an example. Copyright © 2016 John Wiley & Sons, Ltd.     

Almost sure exponential stability of numerical solutions for stochastic delay differential equations with jumps

This paper deals with the almost sure exponential stability of the Euler-type methods for nonlinear stochastic delay differential equations with jumps by using the discrete semimartingale convergence theorem. It is shown that the explicit Euler method reproduces the almost sure exponential stability under an additional linear growth condition. By replacing the linear growth condition with the one-sided Lipschitz condition, the backward Euler method is able to reproduce the stability property.     

Backward Euler-Maruyama method applied to nonlinear hybrid stochastic differential equations with time-variable delay

In this paper, we consider strong convergence and almost sure exponential stability of the backward Euler-Maruyama method for nonlinear hybrid stochastic differential equations with time-variable delay. Under the local Lipschitz condition and polynomial growth condition, it is proved that the backward Euler-Maruyama method is strongly convergent. Additionally, the moment estimates and almost sure exponential stability for the analytical solution are proved. Also, under the appropriate condition, we show that the numerical solutions for the backward Euler-Maruyama methods are almost surely exponentially stable. A numerical experiment is given to illustrate the computational effectiveness and the theoretical results of the method.