Abstract: Federated learning (FL) with differential privacy (DP) is a promising distributed learning framework for protecting user privacy. However, the introduction of DP noise leads to a decrease in ...
We consider a discrete-time nonlinear system with bounded additive disturbance [ x_{t+1} = f(x_t, u_t) + w_t,\quad w_t \in \mathbb{W} ] where (\mathbb{W}) is a known compact disturbance set. Given the ...