Sarnmeta, Panitarn
Loading...
2 results
Now showing 1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, A New Accelerated Viscosity Forward-backward Algorithm with a Linesearch for Some Convex Minimization Problems and its Applications to Data Classification(2023-01-01); ; Suantai, SuthepIn this paper, we focus on solving convex minimization problem in the form of a summation of two convex functions in which one of them is Frecét differentiable. In order to solve this problem, we introduce a new accelerated viscosity forward-backward algorithm with a new linesearch technique. The proposed algorithm converges strongly to a solution of the problem without assuming that a gradient of the objective function is L-Lipschitz continuous. As applications, we apply the proposed algorithm to classification problems and compare its performance with other algorithms mentioned in the literature. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, An Accelerated Convex Optimization Algorithm with Line Search and Applications in Machine Learning(2022-05-01); ; Suantai, SuthepIn this paper, we introduce a new line search technique, then employ it to construct a novel accelerated forward–backward algorithm for solving convex minimization problems of the form of the summation of two convex functions in which one of these functions is smooth in a real Hilbert space. We establish a weak convergence to a solution of the proposed algorithm without the Lipschitz assumption on the gradient of the objective function. Furthermore, we analyze its performance by applying the proposed algorithm to solving classification problems on various data sets and compare with other line search algorithms. Based on the experiments, the proposed algorithm performs better than other line search algorithms.