Distributed Stochastic Approximation with Local Projections
It addresses the problem of distributed constrained optimization for multi-agent systems, but the contribution is incremental as it combines existing techniques.
The paper proposes a distributed stochastic approximation method that ensures iterates stay within the intersection of convex sets using local projections and a nonlinear gossip mechanism, proving convergence under standard assumptions.
We propose a distributed version of a stochastic approximation scheme constrained to remain in the intersection of a finite family of convex sets. The projection to the intersection of these sets is also computed in a distributed manner and a `nonlinear gossip' mechanism is employed to blend the projection iterations with the stochastic approximation using multiple time scales