Competing Adaptive Networks
This work addresses decentralized optimization in competitive team settings, which is incremental as it extends cooperative adaptive networks to include competition.
The paper tackles the problem of decentralized competition among teams of adaptive agents, developing an algorithm for this setting and applying it to decentralized training of generative adversarial neural networks, with analysis of its dynamics.
Adaptive networks have the capability to pursue solutions of global stochastic optimization problems by relying only on local interactions within neighborhoods. The diffusion of information through repeated interactions allows for globally optimal behavior, without the need for central coordination. Most existing strategies are developed for cooperative learning settings, where the objective of the network is common to all agents. We consider in this work a team setting, where a subset of the agents form a team with a common goal while competing with the remainder of the network. We develop an algorithm for decentralized competition among teams of adaptive agents, analyze its dynamics and present an application in the decentralized training of generative adversarial neural networks.