Unified convergence rates and tight lower bounds for Byzantine-robust distributed SGD under stochasticity and general data heterogeneity, showing local momentum reduces stochastic error floors.
We report the best performance (i.e., the smallest error) over all configurations
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
-
Byzantine-Robust Distributed SGD: A Unified Analysis and Tight Error Bounds
Unified convergence rates and tight lower bounds for Byzantine-robust distributed SGD under stochasticity and general data heterogeneity, showing local momentum reduces stochastic error floors.