PDR uses sparse random projection to reduce server computation for Byzantine-robust FL aggregation to O(Mp) while preserving near-optimal convergence rates up to a tunable error inflation factor of (1+ε)/(1-ε).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dimensionality Reduction for Robust Federated Learning: A Theoretical Analysis and Convergence Guarantee
PDR uses sparse random projection to reduce server computation for Byzantine-robust FL aggregation to O(Mp) while preserving near-optimal convergence rates up to a tunable error inflation factor of (1+ε)/(1-ε).