A variance-reduction-based client selection with coalition clustering yields modest accuracy gains over baselines in heterogeneous federated learning, but its convergence guarantee rests on an assumption that the policy is already gradient-aligned.
Given now that C d is positive definite since it is an invertible covariance matrix, then from Sylvester Criterion also its submatrixC d AA is invertible and the thesis follows
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitions
A variance-reduction-based client selection with coalition clustering yields modest accuracy gains over baselines in heterogeneous federated learning, but its convergence guarantee rests on an assumption that the policy is already gradient-aligned.