Back to Search Start Over

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

Authors :
Hanzely, Filip
Kovalev, Dmitry
Richtarik, Peter
Publication Year :
2020

Abstract

We propose an accelerated version of stochastic variance reduced coordinate descent -- ASVRCD. As other variance reduced coordinate descent methods such as SEGA or SVRCD, our method can deal with problems that include a non-separable and non-smooth regularizer, while accessing a random block of partial derivatives in each iteration only. However, ASVRCD incorporates Nesterov's momentum, which offers favorable iteration complexity guarantees over both SEGA and SVRCD. As a by-product of our theory, we show that a variant of Allen-Zhu (2017) is a specific case of ASVRCD, recovering the optimal oracle complexity for the finite sum objective.<br />Comment: 30 pages, 8 figures

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2002.04670
Document Type :
Working Paper