norM-DSGT and norM-ED achieve centralized stochastic proximal-gradient rates for distributed composite objectives, with norM-ED transient time O(n^3/(1-λ)^2).
O LSHEVSKY , Asymptotic network independence and step-size for a distributed subgradient method, Journal of machine learning research, 23 (2022), pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Distributed Normal Map-based Stochastic Proximal Gradient Methods over Networks
norM-DSGT and norM-ED achieve centralized stochastic proximal-gradient rates for distributed composite objectives, with norM-ED transient time O(n^3/(1-λ)^2).