GLL-type Nonmonotone Descent Methods Revisited under Kurdyka-Łojasiewicz Property

Abstract: The purpose of this paper is to extend the full convergence results of the classic GLL-type (Grippo-Lampariello-Lucidi) nonmonotone methods to nonconvex and nonsmooth optimization. We propose a novel iterative framework for the minimization of a proper and lower semicontinuous function $\Phi$. The framework consists of the GLL-type nonmonotone decrease condition for a sequence, a relative error condition for its augmented sequence with respect to a Kurdyka-{\L}ojasiewicz (KL) function $\Theta$, and a relative gap condition for the partial maximum objective value sequence. The last condition is shown to be a product of the prox-regularity of $\Phi$ on the set of cluster points, and to hold automatically under a mild condition on the objective value sequence. We prove that for any sequence and its bounded augmented sequence together falling within the framework, the sequence itself is convergent. Furthermore, when $\Theta$ is a KL function of exponent $\theta\in(0, 1)$, the convergence admits a linear rate if $\theta\in(0, 1/2]$ and a sublinear rate if $\theta\in(1/2, 1)$. As applications, we prove, for the first time, that the two existing algorithms, namely the nonmonotone proximal gradient (NPG) method with majorization and NPG with extrapolation both enjoy the full convergence of the iterate sequences for nonconvex and nonsmooth KL composite optimization problems.