When cyclic coordinate descent outperforms randomized coordinate descent

When cyclic coordinate descent outperforms randomized coordinate descent

The coordinate descent (CD) method is a classical optimization algorithm that has seen a revival of interest because of its competitive performance in machine learning applications. A number of recent papers provided convergence rate estimates for their deterministic (cyclic) and randomized variants...

Full description

Bibliographic Details
Main Authors: Gurbuzbalaban, Mert, Ozdaglar, Asuman E, Parrilo, Pablo A., Vanli, Nuri Denizcan
Other Authors: Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Format: Article
Language:English
Published: Neural Information Processing Systems Foundation, Inc. 2019
Online Access:https://hdl.handle.net/1721.1/121536

Internet

https://hdl.handle.net/1721.1/121536

Similar Items