Interior Point Implementations of Alternating Minimization Training
نویسندگان
چکیده
This paper presents an alternating minimization (AM) algorithm used in the training of radial basis function and linear regressor networks. The algorithm is a modification of a small-step interior point method used in solving primal linear programs. The algorithm has a convergence rate of O( fo,L) iterations where n is a measure of the network size and L is a measure of the resulting solution's accuracy. Two results are presented that specify how aggressively the two steps of the AM may be pursued to ensure convergence of each step of the alternating minimization.
منابع مشابه
Interior 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 Modiied Interior Point Method for Alternating Minimizations Interdisciplinary Studies of Intelligent Systems a Modiied Interior Point Method for Alternating Minimizations
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....
متن کاملAn 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 کاملInterior-Point Method for Nuclear Norm Approximation with Application to System Identification
The nuclear norm (sum of singular values) of a matrix is often used in convex heuristics for rank minimization problems in control, signal processing, and statistics. Such heuristics can be viewed as extensions of l1-norm minimization techniques for cardinality minimization and sparse signal estimation. In this paper we consider the problem of minimizing the nuclear norm of an affine matrix val...
متن کاملGraph Cuts via l1 Norm Minimization
Graph cuts have become an increasingly important tool for solving a number of energy minimization problems in computer vision and other fields. In this paper, the graph cut problem is reformulated as an unconstrained l1 norm minimization that can be solved effectively using interior point methods. This reformulation exposes connections between the graph cuts and other related continuous optimiz...
متن کامل