EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
2445. High-order proximal point method in the nonconvex setting
Invited abstract in session WB-41: Structured nonconvex optimization , stream Nonsmooth Optimization.
Wednesday, 10:30-12:00Room: 97 (building: 306)
Authors (first author is the speaker)
| 1. | Alireza Kabgani
|
| Department of Mathematics, University of Antwerp | |
| 2. | Masoud Ahookhosh
|
| Department of Mathematics, University of Antwerp |
Abstract
The primary objective of this talk is to study exact and inexact versions of the high-order proximal-point methods in the nonconvex setting. The subsequential convergence is investigated by showing the monotonicity of the sequence Lyapunov function values, where our Lyapunov function is the high-order Moreau envelope. We establish the global convergence of the method under Kurdyka-Lojasiewicz inequality. As a specific case study, we will discuss the effectiveness of these algorithms in addressing weakly convex optimization problems through theoretical analyses and numerical results.
Keywords
- Non-smooth Optimization
- Programming, Nonlinear
- Algorithms
Status: accepted
Back to the list of papers