Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Erfan Yazdandoost Hamedani"'
Publikováno v:
Computational Optimization and Applications. 85:653-679
In this paper, we propose a variance-reduced primal-dual algorithm with Bregman distance for solving convex-concave saddle-point problems with finite-sum structure and nonbilinear coupling function. This type of problems typically arises in machine l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7f9b0087bd4757dcd1eba5fcb383aab
https://doi.org/10.1007/s10589-023-00472-5
https://doi.org/10.1007/s10589-023-00472-5
Publikováno v:
IEEE Transactions on Automatic Control. 67:5682-5697
We propose decentralized primal-dual methods for cooperative multi-agent consensus optimization problems over both static and time-varying communication networks, where only local communications are allowed. The objective is to minimize the sum of ag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74fd335602645d4663fdba0eedf49285
https://doi.org/10.1109/tac.2021.3130082
https://doi.org/10.1109/tac.2021.3130082
In this paper, we propose a primal-dual algorithm with a novel momentum term using the partial gradients of the coupling function that can be viewed as a generalization of the method proposed by Chambolle and Pock in 2016 to solve saddle point proble
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d59d08130b1fb640db7541bce41370f2
Publikováno v:
GlobalSIP
We consider cooperative multi-agent consensus optimization problems over an undirected network of agents, where only local communications are allowed. The objective is to minimize the sum of agent-specific convex functions over agent-specific private
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::76a4cf646ae75d8c072d30c481d24f14
https://doi.org/10.1109/globalsip.2017.8309021
https://doi.org/10.1109/globalsip.2017.8309021
We consider cooperative multi-agent resource sharing problems over time-varying communication networks, where only local communications are allowed. The objective is to minimize the sum of agent-specific composite convex functions subject to a conic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::496761cce5c3fe110395ff6d00b54de9
http://arxiv.org/abs/1611.07393
http://arxiv.org/abs/1611.07393
Publikováno v:
ACSSC
We consider cooperative multi-agent resource sharing problems over an undirected network of agents, where only those agents connected by an edge can directly communicate. The objective is to minimize the sum of agent-specific composite convex functio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2a964523a70bead0a40d20407110b3f
https://doi.org/10.1109/acssc.2016.7869152
https://doi.org/10.1109/acssc.2016.7869152