Approximate Steepest Coordinate Descent

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.


Published in:
Proceedings of the 34rd International Conference on Machine Learning
Presented at:
International Conference on Machine Learning (ICML 2017), Sydney, Australia, Aug 6-11, 2017
Year:
2017
Publisher:
PMLR
Laboratories:




 Record created 2017-07-13, last modified 2018-09-13

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)