In this paper,we present a family of gradient projection method with arbitrary initialpoint.The formula of search direction in the method is unitary.The convergent conditions ofthe method are given.When the initial po...In this paper,we present a family of gradient projection method with arbitrary initialpoint.The formula of search direction in the method is unitary.The convergent conditions ofthe method are given.When the initial point is feasible,the family of the method contains severalknown algorithms.When the initial point is infeasible,the method is exactly that given in[6].Finally,we give a new method which has global convergence property.展开更多
In this paper, we give a new generalized gradient projection algorithm for nonlinear optimization problems with arbitrary initial point. This new algorithm has some important advantages as follows: (1) The algorithm d...In this paper, we give a new generalized gradient projection algorithm for nonlinear optimization problems with arbitrary initial point. This new algorithm has some important advantages as follows: (1) The algorithm does not require initial feasible point; (2) It can deal with nonlinear equality and inequality constraints problems; (3) The structure of our algorithm is very simple;(4) Under some mild assumptions, it has global convergence.展开更多
基金Project supported by the National Natural Science Foundation of China
文摘In this paper,we present a family of gradient projection method with arbitrary initialpoint.The formula of search direction in the method is unitary.The convergent conditions ofthe method are given.When the initial point is feasible,the family of the method contains severalknown algorithms.When the initial point is infeasible,the method is exactly that given in[6].Finally,we give a new method which has global convergence property.
文摘In this paper, we give a new generalized gradient projection algorithm for nonlinear optimization problems with arbitrary initial point. This new algorithm has some important advantages as follows: (1) The algorithm does not require initial feasible point; (2) It can deal with nonlinear equality and inequality constraints problems; (3) The structure of our algorithm is very simple;(4) Under some mild assumptions, it has global convergence.
