Egor Shulgin

stochastic gradient descent (2) convex optimization (1) variational inequality (1) convergence analysis (1) distributed learning (1) decentralized optimization (1) variance reduction (1) distributed training (1) communication efficiency (1) convex-concave saddle-point (1) saddle-point problems (1) gradient compression (1) generative adversarial network (1) nesterov acceleration (1) bilinear game (1) stochastic extragradient (1) mini-batch size (1) time-varying network (1) accelerated gradient method (1) dual oracle (1)