High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
Neural Networks , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
FedCGNM uses class-grouped normalized momentum to equalize gradients across imbalanced classes in FL with convergence analysis, plus FedHOO X-armed-bandit method for efficient resampling rate tuning.
citing papers explorer
-
Unveiling High-Probability Generalization in Decentralized SGD
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
-
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
FedCGNM uses class-grouped normalized momentum to equalize gradients across imbalanced classes in FL with convergence analysis, plus FedHOO X-armed-bandit method for efficient resampling rate tuning.