An abstract convergence framework with application to inertial inexact forward--backward methods

Abstract

In this paper we introduce a novel abstract descent scheme suited for the minimization of proper and lower semicontinuous functions. The proposed abstract scheme generalizes a set of properties that are crucial for the convergence of several first-order methods designed for nonsmooth nonconvex optimization problems. Such properties guarantee the convergence of the full sequence of iterates to a stationary point, if the objective function satisfies the Kurdyka-Lojasiewicz property. The abstract framework allows for the design of new algorithms. We propose two inertial-type algorithms with implementable inexactness criteria for the main iteration update step. The first algorithm, i${}^2$Piano, exploits large steps by adjusting a local Lipschitz constant. The second algorithm, iPila, overcomes the main drawback of line-search based methods by enforcing a descent only on a merit function instead of the objective function. Both algorithms have the potential to escape local minimizers (or stationary points) by leveraging the inertial feature. Moreover, they are proved to enjoy the full convergence guarantees of the abstract descent scheme, which is the best we can expect in such a general nonsmooth nonconvex optimization setup using first-order methods. The efficiency of the proposed algorithms is demonstrated on two exemplary image deblurring problems, where we can appreciate the benefits of performing a linesearch along the descent direction inside an inertial scheme.

arXiv comment37 pages, 8 figures

References in corpus (7)

• Splitting methods with variable metric for KL functions
• Douglas-Rachford splitting for nonconvex optimization with application to nonconvex feasibility problems
• Forward-backward quasi-Newton methods for nonsmooth optimization problems
• Insights into analysis operator learning: From patch-based sparse models to higher-order MRFs
• Variable metric inexact line-search based methods for nonsmooth optimization
• On the convergence of a linesearch based proximal-gradient method for nonconvex optimization
• Revisiting loss-specific training of filter-based MRFs for image restoration