Coordinate Descent Algorithms
read the original abstract
Coordinate descent algorithms solve optimization problems by successively performing approximate minimization along coordinate directions or coordinate hyperplanes. They have been used in applications for many years, and their popularity continues to grow because of their usefulness in data analysis, machine learning, and other areas of current interest. This paper describes the fundamentals of the coordinate descent approach, together with variants and extensions and their convergence properties, mostly with reference to convex objectives. We pay particular attention to a certain problem structure that arises frequently in machine learning applications, showing that efficient implementations of accelerated coordinate descent algorithms are possible for problems of this type. We also present some parallel variants and discuss their convergence properties under several models of parallel execution.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Near-optimal Online Traffic Engineering
OnlineTE uses optimization decomposition to enable distributed, near-optimal traffic engineering that reacts in seconds to changes in large WANs and outperforms prior centralized approaches in emulation.
-
One Coordinate at a Time: Convergence Guarantees for Rotosolve in Variational Quantum Algorithms
Rotosolve converges to ε-stationary points for smooth non-convex objectives and ε-suboptimal points under PL, with explicit worst-case rates in the finite-shot regime, outperforming or matching RCD in nuanced ways.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.