Kernel-based learning with guarantees for multi-agent applications
It addresses distributed learning in multi-agent systems, offering theoretical guarantees for applications in noisy environments, but appears incremental as it builds on existing kernel-based methods.
The paper tackles kernel-based learning for multi-agent networks observing a noisy nonlinear phenomenon, proposing an algorithm that requires minimal prior knowledge and provides non-asymptotic high-probability error bounds, with results validated through numerical simulations.
This paper addresses a kernel-based learning problem for a network of agents locally observing a latent multidimensional, nonlinear phenomenon in a noisy environment. We propose a learning algorithm that requires only mild a priori knowledge about the phenomenon under investigation and delivers a model with corresponding non-asymptotic high probability error bounds. Both non-asymptotic analysis of the method and numerical simulation results are presented and discussed in the paper.