(Corrected Version) Push-LSVRG-UP: Distributed Stochastic Optimization over Unbalanced Directed Networks with Uncoordinated Triggered Probabilities

-д хадгалсан:
Номзүйн дэлгэрэнгүй
-д хэвлэсэн:arXiv.org (Dec 18, 2024), p. n/a
Үндсэн зохиолч: Hu, Jinhui
Бусад зохиолчид: Chen, Guo, Li, Huaqing, Shen, Zixiang, Zhang, Weidong
Хэвлэсэн:
Cornell University Library, arXiv.org
Нөхцлүүд:
Онлайн хандалт:Citation/Abstract
Full text outside of ProQuest
Шошгууд: Шошго нэмэх
Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!

MARC

LEADER 00000nab a2200000uu 4500
001 2814623829
003 UK-CbPIL
022 |a 2331-8422 
024 7 |a 10.1109/TNSE.2022.3225229  |2 doi 
035 |a 2814623829 
045 0 |b d20241218 
100 1 |a Hu, Jinhui 
245 1 |a (Corrected Version) Push-LSVRG-UP: Distributed Stochastic Optimization over Unbalanced Directed Networks with Uncoordinated Triggered Probabilities 
260 |b Cornell University Library, arXiv.org  |c Dec 18, 2024 
513 |a Working Paper 
520 3 |a Distributed stochastic optimization, arising in the crossing and integration of traditional stochastic optimization, distributed computing and storage, and network science, has advantages of high efficiency and a low per-iteration computational complexity in resolving large-scale optimization problems. This paper concentrates on resolving a large-scale convex finite-sum optimization problem in a multi-agent system over unbalanced directed networks. To tackle this problem in an efficient way, a distributed consensus optimization algorithm, adopting the push-sum technique and a distributed loopless stochastic variance-reduced gradient (LSVRG) method with uncoordinated triggered probabilities, is developed and named Push-LSVRG-UP. Each agent under this algorithmic framework performs only local computation and communicates only with its neighbors without leaking their private information. The convergence analysis of Push-LSVRG-UP is relied on analyzing the contraction relationships between four error terms associated with the multi-agent system. Theoretical results provide an explicit feasible range of the constant step-size, a linear convergence rate, and an iteration complexity of Push-LSVRG-UP when achieving the globally optimal solution. It is shown that Push-LSVRG-UP achieves the superior characteristics of accelerated linear convergence, fewer storage costs, and a lower per-iteration computational complexity than most existing works. Meanwhile, the introduction of an uncoordinated probabilistic triggered mechanism allows Push-LSVRG-UP to facilitate the independence and flexibility of agents in computing local batch gradients. In simulations, the practicability and improved performance of Push-LSVRG-UP are manifested via resolving two distributed learning problems based on real-world datasets. 
653 |a Algorithms 
653 |a Multiagent systems 
653 |a Convergence 
653 |a Complexity 
653 |a Iterative methods 
653 |a Optimization 
653 |a Distributed processing 
653 |a Computer networks 
700 1 |a Chen, Guo 
700 1 |a Li, Huaqing 
700 1 |a Shen, Zixiang 
700 1 |a Zhang, Weidong 
773 0 |t arXiv.org  |g (Dec 18, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/2814623829/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2305.09181