Diffusion Combinatoric Correntropy Algorithm for Distributed Estimation

Distributed estimation algorithms, when based on the mean-square error criterion, often encounter steady-state misalignment in scenarios where the adaptive network experiences impulsive noise. Addressing this challenge, this paper introduces the diffusion combinatoric correntropy algorithm, which employs the combinatoric correntropy as its cost function. Leveraging the inherent robustness of the combinatoric correntropy cost function, this algorithm effectively mitigates the negative impacts caused by impulse noise. A comprehensive analysis, including experimental simulations, is conducted to evaluate the performance of the diffusion combinatoric maximum correntropy criterion algorithm. The simulation outcomes demonstrate that the proposed algorithm surpasses the diffusion maximum correntropy criterion algorithm in terms of convergence speed and steady-state performance. These simulation results align closely with the theoretical analysis, further validating the effectiveness of the diffusion combinatoric correntropy algorithm.