Decentralized Online Ensembles of Gaussian Processes for Multi-Agent Systems
This work addresses the need for scalable decentralized Bayesian solutions in multi-agent systems, representing an incremental advancement over existing kernel-based methods.
The paper tackled the problem of decentralized Bayesian learning in multi-agent systems by introducing a fully decentralized, asymptotically exact solution for Gaussian processes with an ensembling scheme for hyperparameter selection, achieving competitive performance against Bayesian and frequentist methods on simulated and real-world datasets.
Flexible and scalable decentralized learning solutions are fundamentally important in the application of multi-agent systems. While several recent approaches introduce (ensembles of) kernel machines in the distributed setting, Bayesian solutions are much more limited. We introduce a fully decentralized, asymptotically exact solution to computing the random feature approximation of Gaussian processes. We further address the choice of hyperparameters by introducing an ensembling scheme for Bayesian multiple kernel learning based on online Bayesian model averaging. The resulting algorithm is tested against Bayesian and frequentist methods on simulated and real-world datasets.