On the ergodic convergence rates of a first-order primal-dual algorithm (Q312675)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 6627813
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | On the ergodic convergence rates of a first-order primal-dual algorithm |
scientific article; zbMATH DE number 6627813 |
Statements
On the ergodic convergence rates of a first-order primal-dual algorithm (English)
0 references
16 September 2016
0 references
This paper displays refined ergodic convergence rates for a first-order primal-dual algorithm applied to composite convex-concave saddle-point problems. These new convergence rates are expressed in terms of the primal-dual gap function for accelerated variants of the algorithm. Several computational examples illustrate the performances of the proposed algorithms.
0 references
saddle-point preoblems
0 references
primal-dual algorithms
0 references
first order algorithms
0 references
convergence rates
0 references
ergodic convergence
0 references
0 references
0 references
0 references
0 references
0 references
0 references
0 references
0 references
0 references
0.8667730689048767
0 references
0.8300284743309021
0 references
0.8117282390594482
0 references
0.8092387914657593
0 references
0.8088468313217163
0 references
