Forward-backward-forward dynamics for bilevel equilibrium problem

Abstract

We introduce a forward-backward-forward (FBF) algorithm for solving bilevel equilibrium problem associated with bifunctions on a real Hilbert space. This modifies the forward-backward algorithm by relaxing cocoercivity with monotone and Lipschitzness. Further, we present the FBF dynamical system and investigate the generated trajectory's existence, uniqueness and weak convergence. We illustrate the proposed method for equilibrium problem under saddle point constraint.