|
|
Moscow Conference on Combinatorics and Applications - week 1
2 июня 2021 г. 13:35–14:05, г. Москва, Онлайн
|
|
|
|
|
|
Alexander Rogozin (MIPT, HSE) - Decentralized optimization for saddle point problems with local and global variables
|
Количество просмотров: |
Эта страница: | 46 | Материалы: | 1 |
|
Аннотация:
We consider distributed convex-concave saddle point problems over arbitrary connected undirected networks and propose a decentralized distributed algorithm for their solution. The local functions distributed across the nodes are assumed to have global and local groups of variables. For the proposed algorithm we prove non-asymptotic convergence rate estimates with explicit dependence on the network characteristics. To supplement the convergence rate analysis, we propose lower bounds for strongly-convex-strongly-concave and convex-concave saddle-point problems over arbitrary connected undirected networks. We illustrate the considered problem setting by a particular application to distributed calculation of non-regularized Wasserstein barycenters.
Дополнительные материалы:
рогозин.pdf (547.4 Kb)
|
|