Gradient Tracking Methods for Distributed Stochastic Optimization Problems with Decision-dependent Distributions
This paper aims to seek the performative stable solution and the stationary point of the distributed stochastic optimization problem with decision-dependent distributions, which is a finite-sum stochastic optimization problem over a network and the distribution depends on the decision variables. For the performative stable solution, we propose a distributed algorithm, DSGTD-GD, which combines the distributed … Read more