Zhanhong Jiang

federated learning (1) stochastic optimization (1) deep reinforcement learning (1) continual learning (1) stochastic gradient descent (1) online learning (1) policy gradient (1) sample complexity (1) distributed learning (1) policy learning (1) model aggregation (1) deep learning (1) gradient descent (1) variance reduction (1) distributed training (1) collaborative learning (1) robust learning (1) adversarial attack (1) distributed stochastic gradient descent (1) momentum method (1)