Coordinate Descent Faceoff: Primal or Dual?

Dominik Csiba, Peter Richtárik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Randomized coordinate descent (RCD) methods are state-of-the-art algorithms for training linear predictors via minimizing regularized empirical risk. When the number of examples (n) is much larger than the number of features (d), a common strategy is to apply RCD to the dual problem. On the other hand, when the number of features is much larger than the number of examples, it makes sense to apply RCD directly to the primal problem. In this paper we provide the first joint study of these two approaches when applied to L2-regularized linear ERM. First, we show through a rigorous analysis that for dense data, the above intuition is precisely correct. However, we find that for sparse and structured data, primal RCD can significantly outperform dual RCD even if d ≦ n, and vice versa, dual RCD can be much faster than primal RCD even if n ≦ d. Moreover, we show that, surprisingly, a single sampling strategy minimizes both the (bound on the) number of iterations and the overall expected complexity of RCD. Note that the latter complexity measure also takes into account the average cost of the iterations, which depends on the structure and sparsity of the data, and on the sampling strategy employed. We confirm our theoretical predictions using extensive experiments with both synthetic and real data sets.
Original languageEnglish (US)
Title of host publicationProceedings of Machine Learning Research
PublisherML Research Press
Pages246-267
Number of pages22
StatePublished - Jan 1 2018
Externally publishedYes

Fingerprint

Dive into the research topics of 'Coordinate Descent Faceoff: Primal or Dual?'. Together they form a unique fingerprint.

Cite this