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.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found