Randomness and permutations in coordinate descent methods
Abstract We consider coordinate descent (CD) methods with exact line search on convex quadratic problems. Our main focus is to study the performance of the CD method that use random permutations in each epoch and compare it to the performance of the CD methods that use deterministic orders and rand...
Main Authors: | Gürbüzbalaban, Mert, Ozdaglar, Asuman, Vanli, Nuri D, Wright, Stephen J |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Language: | English |
Published: |
Springer Berlin Heidelberg
2021
|
Online Access: | https://hdl.handle.net/1721.1/131362 |
Similar Items
-
When cyclic coordinate descent outperforms randomized coordinate descent
by: Gurbuzbalaban, Mert, et al.
Published: (2019) -
Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods
by: Vanli, Nuri Denizcan, et al.
Published: (2019) -
Global convergence rate of incremental aggregated gradient methods for nonsmooth problems
by: Vanli, Nuri Denizcan, et al.
Published: (2017) -
Why random reshuffling beats stochastic gradient descent
by: Gürbüzbalaban, M., et al.
Published: (2021) -
Convergence rate of block-coordinate maximization Burer–Monteiro method for solving large SDPs
by: Erdogdu, Murat A, et al.
Published: (2022)