
FESS-GDA, a new algorithm that utilizes smoothing techniques, can be uniformly applied to solve several classes of federated nonconvex minimax problems and achieve new or better analytical convergence results.


coremsg

efficient-federated-minimax-optimization-using-stochastic-smoothed-gradient-descent-ascent


Efficient Federated Minimax Optimization Using Stochastic Smoothed Gradient Descent Ascent


title_rewrite


Our AdaFGDA algorithm efficiently addresses distributed non-convex minimax optimization problems by incorporating adaptive learning rates, achieving lower gradient and communication complexities simultaneously.


Efficient-Adaptive-Federated-Minimax-Optimization-for-Non-Convex-Problems


Efficient Adaptive Federated Minimax Optimization for Non-Convex Problems
