Efficient Greedy Coordinate Descent for Composite Problems

Coordinate descent with random coordinate selection is the current state of the art for many large scale optimization problems. However, greedy selection of the steepest coordinate on smooth problems can yield convergence rates independent of the dimension n, and requiring up to n times fewer iterations. In this paper, we consider greedy updates that are based on subgradients for a class of non-smooth composite problems, which includes L1-regularized problems, SVMs and related applications. For these problems we provide (i) the first linear rates of convergence independent of n, and show that our greedy update rule provides speedups similar to those obtained in the smooth case. This was previously conjectured to be true for a stronger greedy coordinate selection strategy. Furthermore, we show that (ii) our new selection rule can be mapped to instances of maximum inner product search, allowing to leverage standard nearest neighbor algorithms to speed up convergence. We demonstrate the validity of the approach through extensive numerical experiments.