Skip to yearly menu bar Skip to main content


Poster

Approximate Steepest Coordinate Descent

Sebastian Stich · Anant Raj · Martin Jaggi

Gallery #56

Abstract: 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.

Live content is unavailable. Log in and register to view live content