Coordinate Descent with Arbitrary Sampling I: Algorithms and Complexity

Zheng Qu, Peter Richtarik

Research output: Contribution to journalArticlepeer-review


We study the problem of minimizing the sum of a smooth convex function and a convex block-separable regularizer and propose a new randomized coordinate descent method, which we call ALPHA. Our method at every iteration updates a random subset of coordinates, following an arbitrary distribution. No coordinate descent methods capable to handle an arbitrary sampling have been studied in the literature before for this problem. ALPHA is a remarkably flexible algorithm: in special cases, it reduces to deterministic and randomized methods such as gradient descent, coordinate descent, parallel coordinate descent and distributed coordinate descent -- both in nonaccelerated and accelerated variants. The variants with arbitrary (or importance) sampling are new. We provide a complexity analysis of ALPHA, from which we deduce as a direct corollary complexity bounds for its many variants, all matching or improving best known bounds.
Original languageEnglish
Pages (from-to)829-857
Number of pages32
JournalOptimization Methods and Software
Issue number5
Publication statusPublished - 5 Jul 2016


Dive into the research topics of 'Coordinate Descent with Arbitrary Sampling I: Algorithms and Complexity'. Together they form a unique fingerprint.

Cite this