An Ordering Method for the Direct Solution of Saddle-point
نویسنده
چکیده
An ordering method and accompanying factorization for the direct solution of saddlepoint matrices is presented. A simple constraint on ordering together with an assumption on the rank of parts of the matrix are sufficient to guarantee the existence of the LDLT factorization, stability concerns aside. In fact, D may be taken to be a diagonal matrix with ±1 along the diagonal, and be fully determined prior to factorization, giving rise to a “signed Cholesky” factorization. A modified minimum-degree-like algorithm which incorporates this constraint is demonstrated, along with a simple algorithm to modify an existing fill-reducing ordering to respect the constraint. While a stability analysis is lacking, numerical experiments indicate that this is generally sufficient to avoid the need for numerical pivoting during factorization, with clear benefits for performance possible. For example, a highly efficient Cholesky factorization routine, based on separate symbolic and numerical phases and possibly exploiting supernodes, can be easily adapted to this more general class
منابع مشابه
Generalized iterative methods for solving double saddle point problem
In this paper, we develop some stationary iterative schemes in block forms for solving double saddle point problem. To this end, we first generalize the Jacobi iterative method and study its convergence under certain condition. Moreover, using a relaxation parameter, the weighted version of the Jacobi method together with its convergence analysis are considered. Furthermore, we extend a method...
متن کاملSADDLE POINT VARIATIONAL METHOD FOR DIRAC CONFINEMENT
A saddle point variational (SPV ) method was applied to the Dirac equation as an example of a fully relativistic equation with both negative and positive energy solutions. The effect of the negative energy states was mitigated by maximizing the energy with respect to a relevant parameter while at the same time minimizing it with respect to another parameter in the wave function. The Cornell pot...
متن کاملAn efficient modified neural network for solving nonlinear programming problems with hybrid constraints
This paper presents the optimization techniques for solving convex programming problems with hybrid constraints. According to the saddle point theorem, optimization theory, convex analysis theory, Lyapunov stability theory and LaSalleinvariance principle, a neural network model is constructed. The equilibrium point of the proposed model is proved to be equivalent to the optima...
متن کاملA new approach to fuzzy quantities ordering based on distance method and its applications for solving fuzzy linear programming
Many ranking methods have been proposed so far. However, there is yet no method that can always give a satisfactory solution to every situation; some are counterintuitive, not discriminating; some use only the local information of fuzzy values; some produce different ranking for the same situation. For overcoming the above problems, we propose a new method for ranking fuzzy quantities based on ...
متن کاملFabrication of Saddle-Shaped Surfaces by Flame Forming Process
The flame forming process is widely used to manufacture ship hull plates. The saddle-shaped surfaces have different curvatures in perpendicular angles of planes and the manufacturers face an anti-clastic curvature. In this article, the manufacturing of saddle-shaped surfaces utilizing the flame forming process is investigated. The spiral irradiating scheme is used for forming. In order to study...
متن کامل