Add to ORKGThis paper focuses on the distributed optimization of stochastic saddle point problems. The first part of the paper is devoted to lower bounds for the cenralized and decentralized distributed methods for smooth (strongly) convex-(strongly) concave saddle-point problems as well as the near-optimal algorithms by which these bounds are achieved. Next, we present a new federated algorithm for cenralized distributed saddle point problems - Extra Step Local SGD. Theoretical analysis of the new method is carried out for strongly convex-strongly concave and non-convex-non-concave problems. In the experimental part of the paper, we show the effectiveness of our method in practice. In particular, we train GANs in a distributed manner.Comment: 52 page...
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex opt...
Saddle-point problems appear in various settings including machine learning, zero-sum stochastic gam...
The diffusion strategy for distributed learning from streaming data employs local stochastic gradien...
We consider distributed convex-concave saddle point problems over arbitrary connected undirected net...
In recent centralized nonconvex distributed learning and federated learning, local methods are one o...
Variational inequalities in general and saddle point problems in particular are increasingly relevan...
We study solution methods for (strongly-)convex-(strongly)-concave Saddle-Point Problems (SPPs) over...
Large scale convex-concave minimax problems arise in numerous applications, including game theory, r...
In this paper, we propose GT-GDA, a distributed optimization method to solve saddle point problems o...
We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the prob...
Large-scale saddle-point problems arise in such machine learning tasks as GANs and linear models wit...
A number of important problems that arise in various application domains can be formulated as a dist...
This dissertation deals with developing optimization algorithms which can be distributed over a netw...
We propose a new approach for distributed optimization based on an emerging area of theoretical comp...
This thesis considers optimization problems defined over a network of nodes, where each node knows o...
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex opt...
Saddle-point problems appear in various settings including machine learning, zero-sum stochastic gam...
The diffusion strategy for distributed learning from streaming data employs local stochastic gradien...
We consider distributed convex-concave saddle point problems over arbitrary connected undirected net...
In recent centralized nonconvex distributed learning and federated learning, local methods are one o...
Variational inequalities in general and saddle point problems in particular are increasingly relevan...
We study solution methods for (strongly-)convex-(strongly)-concave Saddle-Point Problems (SPPs) over...
Large scale convex-concave minimax problems arise in numerous applications, including game theory, r...
In this paper, we propose GT-GDA, a distributed optimization method to solve saddle point problems o...
We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the prob...
Large-scale saddle-point problems arise in such machine learning tasks as GANs and linear models wit...
A number of important problems that arise in various application domains can be formulated as a dist...
This dissertation deals with developing optimization algorithms which can be distributed over a netw...
We propose a new approach for distributed optimization based on an emerging area of theoretical comp...
This thesis considers optimization problems defined over a network of nodes, where each node knows o...
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex opt...
Saddle-point problems appear in various settings including machine learning, zero-sum stochastic gam...
The diffusion strategy for distributed learning from streaming data employs local stochastic gradien...