iPiano: Inertial Proximal Algorithm for Non-Convex Optimization
arXiv:1404.4805
Abstract
In this paper we study an algorithm for solving a minimization problem composed of a differentiable (possibly non-convex) and a convex (possibly non-differentiable) function. The algorithm iPiano combines forward-backward splitting with an inertial force. It can be seen as a non-smooth split version of the Heavy-ball method from Polyak. A rigorous analysis of the algorithm for the proposed class of problems yields global convergence of the function values and the arguments. This makes the algorithm robust for usage on non-convex problems. The convergence result is obtained based on the \KL inequality. This is a very weak restriction, which was used to prove convergence for several other gradient methods. First, an abstract convergence theorem for a generic algorithm is proved, and, then iPiano is shown to satisfy the requirements of this theorem. Furthermore, a convergence rate is established for the general problem class. We demonstrate iPiano on computer vision problems: image denoising with learned priors and diffusion based image compression.
32pages, 7 figures, to appear in SIAM Journal on Imaging Sciences
Cited by in corpus (8)
- Extrapolated Proximal Subgradient Algorithms for Nonconvex and Nonsmooth Fractional Programs
- Block-proximal methods with spatially adapted acceleration
- Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
- A bi-level view of inpainting - based image compression
- Polyquant CT: direct electron and mass density reconstruction from a single polyenergetic source
- Inertial primal-dual algorithms for structured convex optimization
- Non-ergodic Convergence Analysis of Heavy-Ball Algorithms
- An inertial Tseng's type proximal algorithm for nonsmooth and nonconvex optimization problems