Coordinate Friendly Structures, Algorithms and Applications
This work addresses scalability issues in optimization for researchers and practitioners dealing with high-dimensional datasets, though it is incremental in extending existing coordinate update methods.
The paper tackles the challenge of solving large-scale optimization problems by developing coordinate update methods that decompose problems into simple subproblems, enabling efficient parallel and asynchronous computing. It introduces coordinate-friendly operators to derive new algorithms for machine learning and image processing, demonstrating effectiveness through numerical examples.
This paper focuses on coordinate update methods, which are useful for solving problems involving large or high-dimensional datasets. They decompose a problem into simple subproblems, where each updates one, or a small block of, variables while fixing others. These methods can deal with linear and nonlinear mappings, smooth and nonsmooth functions, as well as convex and nonconvex problems. In addition, they are easy to parallelize. The great performance of coordinate update methods depends on solving simple sub-problems. To derive simple subproblems for several new classes of applications, this paper systematically studies coordinate-friendly operators that perform low-cost coordinate updates. Based on the discovered coordinate friendly operators, as well as operator splitting techniques, we obtain new coordinate update algorithms for a variety of problems in machine learning, image processing, as well as sub-areas of optimization. Several problems are treated with coordinate update for the first time in history. The obtained algorithms are scalable to large instances through parallel and even asynchronous computing. We present numerical examples to illustrate how effective these algorithms are.