LocalSGD gains a proven speedup over minibatch SGD for weakly convex objectives under standard gradient similarity, and SCAFFOLD gains a speedup for non-quadratic functions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
LocalSGD gains a proven speedup over minibatch SGD for weakly convex objectives under standard gradient similarity, and SCAFFOLD gains a speedup for non-quadratic functions.