A Bregman inertial forward-reflected-backward method for nonconvex minimization
From MaRDI portal
Publication:6403886
Abstract: We propose a Bregman inertial forward-reflected-backward (BiFRB) method for nonconvex composite problems. Our analysis relies on a novel approach that imposes general conditions on implicit merit function parameters, which yields a stepsize condition that is independent of inertial parameters. In turn, a question of Malitsky and Tam regarding whether FRB can be equipped with a Nesterov-type acceleration is resolved. Assuming the generalized concave Kurdyka-{L}ojasiewicz property of a quadratic regularization of the objective, we obtain sequential convergence of BiFRB, as well as convergence rates on both the function value and actual sequence. We also present formulae for the Bregman subproblem, supplementing not only BiFRB but also the work of Boc{t}-Csetnek-L'aszl'o and Boc{t}-Csetnek. Numerical simulations are conducted to evaluate the performance of our proposed algorithm.
Recommendations
- A mirror inertial forward-reflected-backward splitting: convergence analysis beyond convexity and Lipschitz smoothness
- Inertial proximal gradient methods with Bregman regularization for a class of nonconvex optimization problems
- Malitsky-Tam forward-reflected-backward splitting method for nonconvex minimization problems
- Two-step inertial Bregman alternating minimization algorithm for nonconvex and nonsmooth problems
- A forward-backward algorithm with different inertial terms for structured non-convex minimization problems
Cited in
(2)
This page was built for publication: A Bregman inertial forward-reflected-backward method for nonconvex minimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6403886)
