PMGT-VR: a Decentralized Proximal-gradient Algorithmic Framework with Variance Reduction

This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed fr...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on pattern analysis and machine intelligence Ročník 48; číslo 1; s. 1 - 12
Hlavní autori: Ye, Haishan, Xiong, Wei, Zhang, Tong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 05.09.2025
Predmet:
Complexity theory
Convergence
Decentralized optimization
Loss measurement
Network topology
Optimization
proximal-gradient
Servers
Symmetric matrices
Topology
Training
variance reduction
Vectors
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which combines several techniques, including multi-consensus, gradient tracking, and variance reduction. The proposed framework imitates centralized algorithms and algorithms under this framework achieve convergence rates similar to that of their centralized counterparts. We also describe and analyze two representative algorithms, PMGT-SAGA and PMGT-LSVRG, and compare them to existing state-of-the-art proximal algorithms. To the best of our knowledge, PMGT-VR is the first linearly convergent decentralized stochastic algorithm that can solve decentralized composite optimization problems. Numerical experiments are provided to demonstrate the effectiveness of the proposed algorithms.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2025.3606874