Zhengmian Hu

stochastic gradient descent (3) variance reduction (3) minimax optimization (3) gradient complexity (3) stochastic gradient (2) nonconvex optimization (2) federated learning (2) communication efficiency (2) large language model (2) non-convex optimization (2) sample complexity (2) bayesian inference (1) neural tangent kernel (1) policy gradient (1) convex optimization (1) bayesian learning (1) one-shot learning (1) distributed learning (1) active learning (1) deep learning theory (1)