• Corpus ID: 245827899

Distributed Nash Equilibrium Seeking over Time-Varying Directed Communication Networks

@article{Nguyen2022DistributedNE,
  title={Distributed Nash Equilibrium Seeking over Time-Varying Directed Communication Networks},
  author={Duong Thuy Anh Nguyen and Duong Tung Nguyen and Angelia Nedi'c},
  journal={ArXiv},
  year={2022},
  volume={abs/2201.02323}
}
We study distributed algorithms for finding a Nash equilibrium (NE) in a class of non-cooperative convex games under partial information. Specifically, each agent has access only to its own smooth local cost function and can receive information from its neighbors in a time-varying directed communication network. To this end, we propose a distributed gradient play algorithm to compute a NE by utilizing local information exchange among the players. In this algorithm, every agent performs a… 

Figures and Tables from this paper

AB/Push-Pull Method for Distributed Optimization in Time-Varying Directed Networks

In this paper, we study the distributed optimization problem for a system of agents embedded in time-varying directed communication networks. Each agent has its own cost function and agents cooperate

Ensuring both Accurate Convergence and Differential Privacy in Nash Equilibrium Seeking on Directed Graphs

An approach that can achieve both accurate convergence and rigorous differential privacy with cumulative privacy budget in distributed Nash equilibrium seeking is proposed, in sharp contrast to existing differential-privacy solutions for networked games that have to trade convergence accuracy for differential privacy.

Differentially-private Distributed Algorithms for Aggregative Games with Guaranteed Convergence

This work proposes a fully distributed equilibrium-computation approach for aggregative games that can achieve both rigorous differential privacy and guaranteed computation accuracy of the Nash equilibrium, in sharp contrast to existing differential-privacy solutions.

Ensure Differential Privacy and Convergence Accuracy in Consensus Tracking and Aggregative Games with Coupling Constraints

The generalized Nash equilibrium (GNE) seeking mechanism and the differential-privacy noise injection mechanism are co-designed and a new consensus-tracking algorithm is proposed that can achieve rigorous differential privacy while maintaining accurate tracking performance, which, to the authors' knowledge, has not been achieved before.

References

SHOWING 1-10 OF 30 REFERENCES

Nash equilibrium seeking under partial-decision information over directed communication networks

This paper proposes a fully-distributed pseudo-gradient scheme, which is guaranteed to converge with linear rate to a Nash equilibrium, under strong monotonicity and Lipschitz continuity of the game mapping.

Fully Distributed Nash Equilibrium Seeking Over Time-Varying Communication Networks With Linear Convergence Rate

We design a distributed algorithm for learning Nash equilibria over time-varying communication networks in a partial-decision information scenario, where each agent can access its own cost function

Geometric Convergence of Gradient Play Algorithms for Distributed Nash Equilibrium Seeking

This work analyzes the restricted strongly monotone property of this mapping and proves geometric convergence of the distributed gradient play under milder assumptions of the Nash equilibrium problem and introduces the Nesterov type acceleration for the gradient play algorithm.

Nash Equilibrium Seeking with Non-doubly Stochastic Communication Weight Matrix

A distributed Nash equilibrium seeking algorithm for networked games in which all players’ cost functions are only dependent on the local neighboring players over an interference digraph and an assumption on the communication digraph such that the players are able to update all the estimates of the players who interfere with their cost functions is designed.

Accelerated Gradient Play Algorithm for Distributed Nash Equilibrium Seeking

It is demonstrated that, similarly to the accelerated algorithms in centralized optimization and variational inequality problems, the accelerated algorithm outperforms GRANE in the convergence rate.

A Passivity-Based Approach to Nash Equilibrium Seeking Over Networks

This paper proposes an augmented gradient-play dynamics with correction, in which players communicate locally only with their neighbors to compute an estimate of the other players’ actions, and exploits incremental passivity properties and shows that a synchronizing, distributed Laplacian feedback can be designed using relative estimates of the neighbors.

Geometric convergence of distributed gradient play in games with unconstrained action sets

Distributed optimization over time-varying directed graphs

This work develops a broadcast-based algorithm, termed the subgradient-push, which steers every node to an optimal value under a standard assumption of subgradient boundedness, which converges at a rate of O (ln t/√t), where the constant depends on the initial values at the nodes, the sub gradient norms, and, more interestingly, on both the consensus speed and the imbalances of influence among the nodes.