Recursive Maximum Correntropy Learning Algorithm With Adaptive Kernel Size

Radmanesh, Hamid; Hajiabadi, Mojtaba

doi:10.1109/tcsii.2017.2778038

Cited by 25 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It indeed determines the magnitude of the weights assigned to each error sample and it is a function of error. Optimizing this bandwidth has been widely addressed in previous work, for instance by minimizing Kullback-Leibler divergence between the true and estimated error distribution, using shape of error distribution measured by its kurtosis, using instantaneous error in each iteration, changing the Gaussian kernel, using hybrid methods and so forth [34,35,36,37,38,39,40,41].…”

Section: A Overview Of MCC and Meementioning

confidence: 99%

Trimmed Minimum Error Entropy for Robust Online Regression

Bahrami¹,

Tuncel²

2021

Preprint

View full text Add to dashboard Cite

In this paper, online linear regression in environments corrupted by non-Gaussian noise (especially heavytailed noise) is addressed. In such environments, the error between the system output and the label also does not follow a Gaussian distribution and there might exist abnormally large error samples (or outliers) which mislead the learning process. The main challenge is how to keep the supervised learning problem least affected by these unwanted and misleading outliers.In recent years, an information theoretic algorithm based on Renyi's entropy, called minimum error entropy (MEE), has been employed to take on this issue. However, this minimization might not result in a desired estimator inasmuch as entropy is shift-invariant, i.e., by minimizing the error entropy, error samples may not be necessarily concentrated around zero. In this paper, a quantization technique is proposed by which not only aforementioned need of setting errors around the origin in MEE is addressed, but also major outliers are rejected from MEE-based learning and MEE performance is improved from convergence rate, steady state misalignment, and testing error points of view.

show abstract

Section: A Overview Of MCC and Meementioning

confidence: 99%

Trimmed Minimum Error Entropy for Robust Online Regression

Bahrami¹,

Tuncel²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, some robustness criteria have been proposed and successfully applied to adaptive filtering algorithms to deal with adaptive signal problems under impulsive noise, such as adaptive wireless channel tracking [11] and blind source decomposition [12]. Some typical robustness criteria include maximum correntropy criterion (MCC) [13][14][15], minimum error entropy (MEE) [16][17][18], generalized MCC [19] and minimum kernel risk-sensitive loss criterion [20]. They are insensitive to large outliers, which improves the performance under impulsive noise.…”

Section: Introductionmentioning

confidence: 99%

Research on Robustness of Geometric Algebra Based Adaptive Filtering Algorithms In Non-Gaussian Environment

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, two new geometric algebra (GA) based adaptive filtering algorithms in non-Gaussian environment are proposed, which are deduced from the robust algorithms based on the minimum error entropy (MEE) criterion and the joint criterion of the MEE and the mean square error (MSE) with the help of GA theory. Some experiments validate the effectiveness and superiority of the GA-MEE and GA-MSEMEE algorithms in α-stable noise environment. At the same time, the GA-MSEMEE algorithm has faster convergence speed compared with the GA-MEE.

show abstract

“…When impulsive noise appears, by incorporating the step-size scaler into the update term, a robust subband algorithm was developed [13]. The correntropy measures the similarity between two variables, which is helpful for suppressing large outliers; thus, the maximum correntropy criterion (MCC) has been used for improving the anti-jamming capability of adaptive filters to impulsive noise, yielding the GD-based MCC [14]- [16] and recursive MCC (RMCC) algorithms [17], [18]. However, these robust recursive algorithms have also high complexity of O(M 2 ) ops.…”

Section: Introductionmentioning

confidence: 99%

DCD-Based Recursive Adaptive Algorithms Robust Against Impulsive Noise

Zheng

et al. 2020

IEEE Trans. Circuits Syst. II

View full text Add to dashboard Cite

The dichotomous coordinate descent (DCD) algorithm has been successfully used for significant reduction in the complexity of recursive least squares (RLS) algorithms. In this work, we generalize the application of the DCD algorithm to RLS adaptive filtering in impulsive noise scenarios and derive a unified update formula. By employing different robust strategies against impulsive noise, we develop novel computationally efficient DCDbased robust recursive algorithms. Furthermore, to equip the proposed algorithms with the ability to track abrupt changes in unknown systems, a simple variable forgetting factor mechanism is also developed. Simulation results for channel identification scenarios in impulsive noise demonstrate the effectiveness of the proposed algorithms.

show abstract

Recursive Maximum Correntropy Learning Algorithm With Adaptive Kernel Size

Cited by 25 publications

References 34 publications

Trimmed Minimum Error Entropy for Robust Online Regression

Trimmed Minimum Error Entropy for Robust Online Regression

Research on Robustness of Geometric Algebra Based Adaptive Filtering Algorithms In Non-Gaussian Environment

DCD-Based Recursive Adaptive Algorithms Robust Against Impulsive Noise

Contact Info

Product

Resources

About