New clipped federated methods with local steps and random reshuffling are proven to converge under (L0,L1)-smoothness, recovering known rates when L1=0.
For such p, we have L0 + L1 ∇f ˆxtp = ˆap ≤ 2L1 ∇f ˆxtp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
New clipped federated methods with local steps and random reshuffling are proven to converge under (L0,L1)-smoothness, recovering known rates when L1=0.