Accelerated Bregman gradient methods for relatively smooth and relatively Lipschitz continuous minimization problems

Abstract: In this paper, we propose some accelerated methods for solving optimization problems under the condition of relatively smooth and relatively Lipschitz continuous functions with an inexact oracle. We consider the problem of minimizing the convex differentiable and relatively smooth function concerning a reference convex function. The first proposed method is based on a similar triangles method with an inexact oracle, which uses a special triangular scaling property for the used Bregman divergence. The other proposed methods are non-adaptive and adaptive (tuning to the relative smoothness parameter) accelerated Bregman proximal gradient methods with an inexact oracle. These methods are universal in the sense that they are applicable not only to relatively smooth but also to relatively Lipschitz continuous optimization problems. We also introduced an adaptive intermediate Bregman method which interpolates between slower but more robust algorithms non-accelerated and faster, but less robust accelerated algorithms. We conclude the paper with the results of numerical experiments demonstrating the advantages of the proposed algorithms for the Poisson inverse problem.