Diffusion maximum correntropy criterion algorithms for robust distributed estimation

Abstract

Abstract:Robust diffusion adaptive estimation algorithms based on the maximum correntropy criterion (MCC), including adaptation to combination MCC and combination to adaptation MCC, are developed to deal with the distributed estimation over network in impulsive (long-tailed) noise environments. The cost functions used in distributed estimation are in general based on the mean square error (MSE) criterion, which is desirable when the measurement noise is Gaussian. In non-Gaussian situations, such as the impulsive-noise case, MCC based methods may achieve much better performance than the MSE methods as they take into account higher order statistics of error distribution. The proposed methods can also outperform the robust diffusion least mean p-power(DLMP) and diffusion minimum error entropy (DMEE) algorithms. The mean and mean square convergence analysis of the new algorithms are also carried out.

A robust correntropy based subspace tracking algorithm in impulsive noise environments

“…Different from the conventional MSE criterion, MCC demonstrates the inherent robustness to outliers in adaptive filtering, that is, when the magnitude of the estimation error is small, just like MSE, MCC measures the L2 norm distance between the system outputs and the observations, otherwise, when the magnitude of the estimation error gets larger, MCC measure the L1 norm distance and eventually the L0 norm distance between the system outputs and the observations. The MCC criterion based cost function has been widely employed in PCA methods, state space filters, diffusion adaptive estimation, DOA estimation, etc [14][15][16][17]. In this paper, we apply MCC as a substitute for the conventional MSE criterion in the PAST algorithm.…”

Transient performance analysis of adaptive multitask network based on correntropy criterion

“…Correntropy criterion is a generalized correlation function of 2 random variables, which measures the similarity between them. [19][20][21][22][23][24][25][26][27][28][29][30][31] For 2 random variable d k (i) and y k (i), we can define the correntropy correlation function as follows:…”

“…Thus, when the combination coefficients are symmetric and convex such as Equation 23, we will find out that optimizing the global cost in view of individual costs (12) is equivalent to optimizing the global cost in view of local costs (27). Hence, we can represent the global optimization problem in terms of the local optimization problem.…”

“…In our previous works, 17,18 the multitask learning over adaptive networks is derived based on maximum correntropy criterion (MCC). [19][20][21][22][23][24][25][26][27][28][29][30][31] The proposed learning algorithm determines a novel cooperation policy for sensors, in which they can collaborate with neighbors that have similar task and they can reject the collaboration of neighbors that have distinct tasks. In this paper, we want to analyze the transient performance of our proposed learning algorithm 17,18 and compare the theoretical results with simulation results.…”

Adaptive multitask network based on maximum correntropy learning algorithm

“…16,17 One useful way to extract similarities among objectives is to formulate optimization problems based on information theoretic learning cost functions. [18][19][20][21][22][23][24][25][26][27][28][29][30] Maximum correntropy criterion (MCC) is one of the useful measures of similarity that has been considered in learning problems recently. 25 In this paper, we investigate multitask learning over adaptive networks under different situations that are contrary from the former works.…”