Inertial Three-Operator Splitting Method and Applications

Abstract

We introduce an inertial variant of the forward-Douglas-Rachford splitting and analyze its convergence. We specify an instance of the proposed method to the three-composite convex minimization template. We provide practical guidance on the selection of the inertial parameter based on the adaptive starting idea. Finally, we illustrate the practical performance of our method in various machine learning applications.

arXiv commentThis work is presented at SIAM Conference on Optimization (OP17) in Vancouver, British Columbia, Canada on the 23rd of May 2017 by Bang Cong Vu

References in corpus (6)

• Sparse and stable Markowitz portfolios
• An inertial forward-backward algorithm for monotone inclusions
• Generalized Forward-Backward Splitting
• The rate of convergence of Nesterov's accelerated forward-backward method is actually faster than $1/k^2$
• An inertial three-operator splitting algorithm with applications to image inpainting
• Stochastic Three-Composite Convex Minimization