Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems

Abstract

In this paper we study nonconvex and nonsmooth optimization problems with semi-algebraic data, where the variables vector is split into several blocks of variables. The problem consists of one smooth function of the entire variables vector and the sum of nonsmooth functions for each block separately. We analyze an inertial version of the Proximal Alternating Linearized Minimization (PALM) algorithm and prove its global convergence to a critical point of the objective function at hand. We illustrate our theoretical findings by presenting numerical experiments on blind image deconvolution, on sparse non-negative matrix factorization and on dictionary learning, which demonstrate the viability and effectiveness of the proposed method.

Cited by in corpus (11)

• Bregman Proximal Framework for Deep Linear Neural Networks
• An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration
• Short-and-Sparse Deconvolution -- A Geometric Approach
• Compressed Sensing Microscopy with Scanning Line Probes
• Model Function Based Conditional Gradient Method with Armijo-like Line Search
• PALMNUT: An Enhanced Proximal Alternating Linearized Minimization Algorithm with Application to Separate Regularization of Magnitude and Phase
• Bregman Proximal Gradient Algorithm with Extrapolation for a class of Nonconvex Nonsmooth Minimization Problems
• An accelerated proximal iterative hard thresholding method for ${\ell }_0$ minimization
• Inertial Bregman Proximal Gradient Algorithm For Nonconvex Problem with Smooth Adaptable Property
• Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
• Linear Convergence of a Proximal Alternating Minimization Method with Extrapolation for ${\ell }_1$-Norm Principal Component Analysis