EUROPT 2024
Abstract Submission

90. Scaled gradient methods under convexity and local smoothness

Invited abstract in session TD-5: Nonsmooth optimization algorithms, stream Nonsmooth and nonconvex optimization algorithms.

Thursday, 14:10 - 15:50
Room: M:N

Authors (first author is the speaker)

1. Susan Ghaderi
ESAT, KU Leuven
2. Yves Moreau
KU Leuven
3. Masoud Ahookhosh
Department of Mathematics, University of Antwerp

Abstract

This paper explores the unconstrained minimization of smooth convex functions with locally Lipschitz gradients, focusing on the Scaled Gradient Method (SGA) and its adaptive version, AdaSGA. We analyze their convergence, complexity under local smoothness, and effectiveness through numerical experiments. Our findings, particularly applied to Poisson linear inverse problems, showcase the potential of these methods in optimization and computational applications.

Keywords

Status: accepted


Back to the list of papers