A Modiied Interior Point Method for Alternating Minimizations Interdisciplinary Studies of Intelligent Systems a Modiied Interior Point Method for Alternating Minimizations
نویسنده
چکیده
Optimization of non-linear performance functionals subject to constraints is a typical problem in control and there exist many diierent optimization methods. These methods, however, can take a long time to converge to optimal solutions. This paper presents a modiied interior point algorithm that optimizes a class of performance func-tionals possessing both linear and non-linear characteristics. The optimization is an alternating minimization (AM) of the linear and non-linear characteristics. The algorithm presented, based upon typical interior point methods from Linear Programming, is fast, requiring O(p n) iterations to nd a local optimum, and computationally ee-cient requiring O(n 3:5) computations to solve the problem. Conditions are speciied for the non-linear optimization to guarantee convergence of the algorithm to local optima. Results are presented demonstrating the rates and convergence to local minima. These AM methods are useful in the design of distributed supervisory controllers for large scale systems.
منابع مشابه
An Hybrid Interior Point Algorithm for Performing Alternating Minimizations an Hybrid Interior Point Algorithm for Performing Alternating Minimizations
Optimization using alternating minimization (AM) alternately minimizes an objective function with respect to two disjoint subsets of a function's parameters. AM algorithms are useful for optimization problems which can be decomposed into convex subproblems. AM algorithms have recently appeared in the neural computing community. This paper examines the use of recently developed Interior Point (I...
متن کاملFinal Iterations in Interior Point Methods | Preconditioned Conjugate Gradients and Modiied Search Directions
In this article we consider modiied search directions in the endgame of interior point methods for linear programming. In this stage, the normal equations determining the search directions become ill-conditioned. The modiied search directions are computed by solving perturbed systems in which the systems may be solved ef-ciently by the preconditioned conjugate gradient solver. We prove the conv...
متن کاملOn the Complexity of a Class of Projective Interior Point Methods
In this paper we present a generic projective interior point algorithm for linear programming which includes modiied versions of Karmarkar's original algorithm and most other projective algorithms that have been proposed as special cases. We show that this class of algorithms has a worst case iteration bound of O(p nL) and is closely related to the class of potential reduction interior point me...
متن کاملInterior Point Implementations of Alternating Minimization Training Interior Point Implementations of Alternating Minimization Training
This paper presents an alternating minimization algorithm used to train radial basis function networks. The algorithm is a modiication of an interior point method used in solving primal linear programs. The resulting algorithm is shown to have a convergence rate on the order of p nL iterations where n is a measure of the network size and L is a measure of the resulting solution's accuracy.
متن کاملA superquadratic infeasible-interior-point method for linear complementarity problems
We consider a modiication of a path-following infeasible-interior-point algorithm described by Wright. In the new algorithm, we attempt to improve each major iterate by reusing the coeecient matrix factors from the latest step. We show that the modiied algorithm has similar theoretical global convergence properties to those of the earlier algorithm, while its asymptotic convergence rate can be ...
متن کامل