On the dynamics of multi agent nonlinear filtering and learning
This work addresses decentralized learning challenges for researchers in signal processing and computational intelligence, but appears incremental as it builds on existing multiagent frameworks.
The paper tackles the problem of achieving cohesive learning behavior in multiagent networked systems with nonlinear filtering/learning dynamics, presenting a general formulation and conditions for consensus, with applications demonstrated in distributed and federated learning scenarios.
Multiagent systems aim to accomplish highly complex learning tasks through decentralised consensus seeking dynamics and their use has garnered a great deal of attention in the signal processing and computational intelligence societies. This article examines the behaviour of multiagent networked systems with nonlinear filtering/learning dynamics. To this end, a general formulation for the actions of an agent in multiagent networked systems is presented and conditions for achieving a cohesive learning behaviour is given. Importantly, application of the so derived framework in distributed and federated learning scenarios are presented.