Modified Information Theoretic Criteria for Low Complexity Estimation of the Amount of Components in MEG Measurements

2019 ◽  
Author(s):  
Elnaz Javidi ◽  
Joao Paulo C. L. da Costa ◽  
Ricardo K. Miranda ◽  
Joao Paulo A. Maranhao ◽  
Jose A. R. Vargas
Keyword(s):  
Low Complexity ◽  
Information Theoretic ◽  
Complexity Estimation ◽  
Information Theoretic Criteria

Online minimum error entropy algorithm with unbounded sampling

2019 ◽  
Vol 17 (02) ◽  
pp. 293-322 ◽  
Author(s):  
Cheng Wang ◽  
Ting Hu
Keyword(s):  
Hilbert Spaces ◽  
Reproducing Kernel ◽  
Regression Function ◽  
Optimization Method ◽  
Low Complexity ◽  
Learning Ability ◽  
Information Theoretic ◽  
Minimum Error ◽  
Information Theoretic Learning ◽  
Kernel Hilbert Spaces

Minimum error entropy (MEE) criterion is an important optimization method in information theoretic learning (ITL) and has been widely used and studied in various practical scenarios. In this paper, we shall introduce the online MEE algorithm for dealing with big datasets, associated with reproducing kernel Hilbert spaces (RKHS) and unbounded sampling processes. Explicit convergence rate will be given under the conditions of regularity of the regression function and polynomially decaying step sizes. Besides its low complexity, we will also show that the learning ability of online MEE is superior to the previous work in the literature. Our main techniques depend on integral operators on RKHS and probability inequalities for random variables with values in a Hilbert space.

Sign in / Sign up

Export Citation Format

Share Document