— We come up with novel quantized averaging algorithms on synchronous and asynchronous communication networks with fixed, switching and random topologies. The implementation of ...
We study randomized variants of two classical algorithms: coordinate descent for systems of linear equations and iterated projections for systems of linear inequalities. Expanding...
— We study the problem of reaching a consensus in the values of a distributed system of agents with time-varying connectivity in the presence of delays. We consider a widely stud...
Pierre-Alexandre Bliman, Angelia Nedic, Asuman E. ...
The average consensus problem in the distributed signal processing context is addressed by linear iterative algorithms, with asymptotic convergence to the consensus. The convergen...
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...