Back to Search
Start Over
Insights Into the Robustness of Minimum Error Entropy Estimation.
- Source :
-
IEEE transactions on neural networks and learning systems [IEEE Trans Neural Netw Learn Syst] 2018 Mar; Vol. 29 (3), pp. 731-737. Date of Electronic Publication: 2016 Dec 22. - Publication Year :
- 2018
-
Abstract
- The minimum error entropy (MEE) is an important and highly effective optimization criterion in information theoretic learning (ITL). For regression problems, MEE aims at minimizing the entropy of the prediction error such that the estimated model preserves the information of the data generating system as much as possible. In many real world applications, the MEE estimator can outperform significantly the well-known minimum mean square error (MMSE) estimator and show strong robustness to noises especially when data are contaminated by non-Gaussian (multimodal, heavy tailed, discrete valued, and so on) noises. In this brief, we present some theoretical results on the robustness of MEE. For a one-parameter linear errors-in-variables (EIV) model and under some conditions, we derive a region that contains the MEE solution, which suggests that the MEE estimate can be very close to the true value of the unknown parameter even in presence of arbitrarily large outliers in both input and output variables. Theoretical prediction is verified by an illustrative example.
Details
- Language :
- English
- ISSN :
- 2162-2388
- Volume :
- 29
- Issue :
- 3
- Database :
- MEDLINE
- Journal :
- IEEE transactions on neural networks and learning systems
- Publication Type :
- Academic Journal
- Accession number :
- 28026787
- Full Text :
- https://doi.org/10.1109/TNNLS.2016.2636160