Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Ou, Hongjia"'
Autor:
Ou, Hongjia, Themelis, Andreas
Publikováno v:
2024 10th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 2802-2807
Leveraging on recent advancements on adaptive methods for convex minimization problems, this paper provides a linesearch-free proximal gradient framework for globalizing the convergence of popular stepsize choices such as Barzilai-Borwein and one-dim
Externí odkaz:
http://arxiv.org/abs/2404.09617
Publikováno v:
J Optim Theory Appl (2024)
This work investigates a Bregman and inertial extension of the forward-reflected-backward algorithm [Y. Malitsky and M. Tam, SIAM J. Optim., 30 (2020), pp. 1451--1472] applied to structured nonconvex minimization problems under relative smoothness. T
Externí odkaz:
http://arxiv.org/abs/2212.01504
Publikováno v:
Journal of Optimization Theory & Applications; Nov2024, Vol. 203 Issue 2, p1127-1159, 33p
The use of momentum to accelerate convergence of first-order algorithms has been gaining renewed interest ever since its first appearance 60 years back. Initially inspired by the physics intuition that inertia is effective in preventing oscillatory b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::d7b32f59b9231d462358bf9438ac7678
http://hdl.handle.net/2324/6790347
http://hdl.handle.net/2324/6790347