An accelerated randomized Bregman-Kaczmarz method for strongly convex linearly constraint optimization

Abstract

In this paper, we propose a randomized accelerated method for the minimization of a strongly convex function under linear constraints. The method is of Kaczmarz-type, i.e. it only uses a single linear equation in each iteration. To obtain acceleration we build on the fact that the Kaczmarz method is dual to a coordinate descent method. We use a recently proposed acceleration method for the randomized coordinate descent and transfer it to the primal space. This method inherits many of the attractive features of the accelerated coordinate descent method, including its worst-case convergence rates. A theoretical analysis of the convergence of the proposed method is given. Numerical experiments show that the proposed method is more efficient and faster than the existing methods for solving the same problem.

6 pages, 5 figures, 2023 European Control Conference (ECC)

References in corpus (5)

• Paved with Good Intentions: Analysis of a Randomized Block Kaczmarz Method
• Randomized Extended Kaczmarz for Solving Least-Squares
• Randomized Iterative Methods for Linear Systems
• Preasymptotic Convergence of Randomized Kaczmarz Method
• Restarting accelerated gradient methods with a rough strong convexity estimate