kkt

In order to increase training speed of original on-line support vector machine training algorithm, and to deal with the case of margin support vector set being empty, a new algorithm was obtained by strict mathematical deduction based on KKT condition and Lagrangian multiplier method.

针对支持向量机在线训练算法训练速度较慢和无法处理边缘支持向量集合为空的缺点，以KKT条件和拉格朗日乘数法为基础，用严格的数学推导得到一种改进的训练算法。

Methods Learning Motivation Factors Test ( KKT) was conducted on 1,186 middle school students.

方法采用学习动力因素测验（KKT）对1186名中学生测试。

By the KKT condition of solution procedure, samples in training set can be divided into three categories.

通过分析支持向量机求解二次规划中的KKT条件，根据样本的判决值，可以将训练集中的样本划分为不同的类别。

First of all, we transform the Euclidean distance model into a sequence of least squares problems, from the non-negativity constrained least squares' KKT conditions we have a linear complementarity problem ( LCP), and then a new algorithm for NMF based on LCP is proposed.

首先我们把欧氏距离模型转化为序列非负最小二乘问题，然后根据非负最小二乘问题的KKT条件转化为线性互补问题，基于线性互补问题我们提出了一种NMF算法。

Study on optimal power flow based on primal-dual interior point algorithm under perturbed KKT conditions and branch-and-bound method

基于扰动KKT条件的原始-对偶内点法和分支定界法的最优潮流研究

A BFGS Method for Solving KKT Systems of Constrained Optimization Problems

求解约束最优化问题KKT系统的BFGS方法

Comparing condition number with structured condition number for KKT systems

KKT系统结构条件数与条件数的比较

Structured sensitivity analysis for a class of KKT systems

一类KKT系统的结构敏度分析

Based on the homogenization effect of min max principle, a new merit function is presented, so that a self adjusting function is embedded into perturbed KKT conditions for primal dual interior point methods.

基于极大极小原理的均匀化作用，构造了一个新的效益函数，从而在原-对偶内点方法的摄动KKT条件里嵌入一种自调节功能。

New model and algorithm for solving the KKT system of optimal power flow

求解最优潮流KKT系统的一类新模型及算法设计