Question about pFedMeOptimizer. about pfedme HOT 2 CLOSED

Hi siddharthdivi,
Mu in here is a kind of regularization inside f_i(\theta).
For example: The local optimization problem for each client is defined as $theta_i = min( f_i(\theta_i) + \frac{\lamda}{2}(theta_i -w))$. I can consider the f_i(\theta_i) is cross entropy loss function with regularization $\frac{mu}{2}(theta_i)^2$ inside. So here $\mu$ is regularization term to make f_i function becomes strongly-convex

from pfedme.

Thanks for the explanation!

from pfedme.