约束非线性最小二乘的极大熵方法

A Maximum Entropy Method for the Constrained Nonlinear Least Square

研究一种将变尺度方法与极大熵方法相结合的新方法，并将其用于约束非线性最小二乘问题，这是一种对有约束和无约束非线性最小二乘问题的统一算法，实现了对Ｈｅｓｓｅ矩阵的整体逼近．新方法具有显式搜索方向，因而在迭代中不需要求解二次规划子问题．

Constrained nonlinear least square (CNLS) is widely used in the engineering and economic fields. A new algorithm which is a combination of the variable metric method and the maximum entropy method is studied and used in CNIS. It is characterized by explicit search direction and so it is not necessary to solve the quadratic programming subproblem during iteration. Numerical results show that it is useful to CNLS.