Approximate Steepest Coordinate Descent


Sebastian U. Stich, Anant Raj, Martin Jaggi ;
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3251-3259, 2017.


We propose a new selection rule for the coordinate selection in coordinate descent methods for huge-scale optimization. The efficiency of this novel scheme is provably better than the efficiency of uniformly random selection, and can reach the efficiency of steepest coordinate descent (SCD), enabling an acceleration of a factor of up to $n$, the number of coordinates. In many practical applications, our scheme can be implemented at no extra cost and computational efficiency very close to the faster uniform selection. Numerical experiments with Lasso and Ridge regression show promising improvements, in line with our theoretical guarantees.

Related Material