Article ID: | iaor19971063 |
Country: | Netherlands |
Volume: | 71 |
Issue: | 1 |
Start Page Number: | 17 |
End Page Number: | 28 |
Publication Date: | Nov 1995 |
Journal: | Mathematical Programming (Series A) |
Authors: | Kim Sehun, Chang Kun-Nyeong, Lee Jun-Yeon |
Most of the descent methods developed so far suffer from the computational burden due to a sequence of constrained quadratic subproblems which are needed to obtain a descent direction. In this paper the authors present a class of proximal-type descent methods with a new direction-finding subproblem. Especially, two of them have a linear programming subproblem instead of a quadratic subproblem. Computational experience of these two methods has been performed on two well-known test problems. The results show that these methods are another very promising approach for nondifferentiable convex optimization.