The authors derive a clipped gradient tracking method with staggered variance reduction for RUC-regular finite-sum distributed optimization problems, establishing an O(∑ n_i^{1.5} + n_i^{0.5} ε^{-1}) complexity bound that relies only on local smoothness.
A descent lemma beyond lipschitz gradient continuity: first-order methods revisited and applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Clipped Stochastic Gradient Tracking For Locally Smooth Functions
The authors derive a clipped gradient tracking method with staggered variance reduction for RUC-regular finite-sum distributed optimization problems, establishing an O(∑ n_i^{1.5} + n_i^{0.5} ε^{-1}) complexity bound that relies only on local smoothness.