SAGDA: AchievingO(2)Communication ComplexityinFederatedMin-MaxLearning
–Neural Information Processing Systems
Compared with conventional minimization problems (e.g., empirical risk minimization), min-max optimization has aricher mathematical structure, thus being able tomodel more sophisticated learning problems thatemergefrom ever-emerging applications.
Neural Information Processing Systems
Feb-8-2026, 03:55:23 GMT