Proximal gradient methods beyond monotony
arXiv:2211.04827 · doi:10.46298/jnsao-2023-10290
Abstract
We address composite optimization problems, which consist in minimizing the sum of a smooth and a merely lower semicontinuous function, without any convexity assumptions. Numerical solutions of these problems can be obtained by proximal gradient methods, which often rely on a line search procedure as globalization mechanism. We consider an adaptive nonmonotone proximal gradient scheme based on an averaged merit function and establish asymptotic convergence guarantees under weak assumptions, delivering results on par with the monotone strategy. Global worst-case rates for the iterates and a stationarity measure are also derived. Finally, a numerical example indicates the potential of nonmonotonicity and spectral approximations.
arXiv comment18 pages, 1 algorithm, 1 figure
References in corpus (4)
- Forward-backward envelope for the sum of two nonconvex functions: Further properties and nonmonotone line-search algorithms
- Constrained composite optimization and augmented Lagrangian methods
- Proximal Gradient Algorithms under Local Lipschitz Gradient Continuity: A Convergence and Robustness Analysis of PANOC
- Implicit augmented Lagrangian and generalized optimization