查询词典 acceleration of convergence

With a view of this, we propose the key theorem and discuss the bounds on the rate of uniform convergence of learning processes based on ERM principle when samples are corrupted by zero-expect noise.

基于此种考虑，本文提出了样本受零均值噪声影响下的学习理论的关键定理，并讨论了零均值噪声样本下的学习过程一致收敛速度的界。

In this paper a decision method of uniform convergence for function sequence is given, and a few of properties for the uniformly convergent function-sequence are obtained by this method, which is used in the construction of a new uniformly convergent function-sequence by others known.

给出了一个定理用于判定函数列的一致收敛，通过此判定定理，又得出了由一致收敛函数列构造新的一致收敛函数列的几个性质。

The Lyapunov stability of the proposed robust decentralized controller is analyzed, and the global uniform ultimate boundedness stability with exponential convergence is proved.

对所设计的关节分散鲁棒控制器的 Lyapunov 稳定性进行了分析，证明系统是指数收敛全局一致最终有界稳定的。

In the forth chapter, the convergence problem of three Ishikawa and modified three Ishikawa iterative sequences under uniformly continuousΦ-strongly pseudo-contractive mapping and approximating pseudo-contractive mapping is

第四章主要讨论了三重迭代序列以及修改了的三重迭代序列在一致连续的Φ-强伪压缩映射、渐近伪压缩映象下的收敛问题，给出了其判别准则和结论描述。

The existence of pointwise robust convergent algorithm and uniformly robust convergence is next investigated. We propose an optimal l〓 robustness synthesis method for structured perturbations system by taking advantage of the famous Small Gain Theorem.

证明了最优l〓辨识算法的存在性；证明了黑箱辨识存在辨识算法使全局误差收敛于有界区间；提出并证明了逐点鲁棒收敛算法的存在性；证明了一致鲁棒收敛算法的存在性。

In this paper, the problem of an iterative sequence approximation a common fixed point for nonexpansive non-self mappings is studied in real uniformly convex Banach space, then we obtain a strongly convergence theorem.

在实一致凸Banach空间中，讨论了关于非扩张非自映射序列逼近公共不动点的问题，获得了一个强收敛定理，改进和推广了现有文献的一些相应结果。

The objective of Chapter 2 is to give the weak convergence theorem of S ={T1 :t E G of asymptotically nonexpansive mappings in a uniformly convex Banach space without assuming that X has a Frechet differentiable norm.

本文第二章在G仅要求是一个定向网，X为不具有范数Frechet可微条件的一致凸Banach空间的情况下，给出了一族渐近非扩张映射的弱收敛定理。

A class of modified BFGS algorithm which satisfies the new quasi-Newton equation is proposed in the paper[1],and the global convergence of the algorithm is proved under the condition that the objective function is uniformly convex.

文献[1]曾在已建立的一类新拟牛顿方程 Bk+1sk=yk-=yk+kγskTsksk的基础上，证明了满足新拟牛顿方程的一类改进BFGS算法在目标函数为一致凸的条件下，具有全局收敛性。

In this paper,several quasi-Newton algorithms are generalized to a class of new quasi-Newton equation,several modified quasi-Newton algorithm s are obtained and their global convergence are proved under the objective function is uniformly convex.

将几个拟牛顿算法推广到一类新拟牛顿方程，得到几个修正拟牛顿算法；在目标函数为一致凸的条件下，证明了它们都具有全局收敛性。

Under certain conditions, we prove the global convergence of the modified Broydens class of quasi-Newton methods for solving uniformly convex minimization problems.

并证明算法用于求解一致凸函数极小化问题时的全局收敛性。

Nowadays, most of research are to build a transmutative Petri Nets through adding controlling place sets, controlling arc sets and controlling policy to the basic Petri Nets, while the Controlled Petri Nets could be used to argue many controlling theory problems conveniently and to induce many logically and physically supervisory and solve the Event Feedback Controlling Problems and State Feedback Controlling Problem in DEDS supervisory theory.

目前大多数的研究表现为在变形后的受控Petri网基础上，利用各种方法求得各种逻辑型、结构型控制器，解决DEDS监控理论中的事件反馈控制问题与状态反馈控制问题。

On one hand, there are discussions with the works council and union about extension of short time working up to the end of September.

一方面，有讨论，工程理事会和联盟关于延长工作时间短至9月底。