In a potential game model of federated learning, the unique Nash equilibrium training effort jumps discontinuously at a critical reward factor, which the paper proposes as the optimal server reward.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Nonlinear Equilibrium Transitions in a Potential Game Model for Federated Learning
In a potential game model of federated learning, the unique Nash equilibrium training effort jumps discontinuously at a critical reward factor, which the paper proposes as the optimal server reward.