Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

April 2014, Vol. 26, No. 4, Pages 739-760
(doi: 10.1162/NECO_a_00566)
© 2014 Massachusetts Institute of Technology
Refined Rademacher Chaos Complexity Bounds with Applications to the Multikernel Learning Problem
Article PDF (197.83 KB)
Abstract

Estimating the Rademacher chaos complexity of order two is important for understanding the performance of multikernel learning (MKL) machines. In this letter, we develop a novel entropy integral for Rademacher chaos complexities. As compared to the previous bounds, our result is much improved in that it introduces an adjustable parameter ϵ to prohibit the divergence of the involved integral. With the use of the iteration technique in Steinwart and Scovel (2007), we also apply our Rademacher chaos complexity bound to the MKL problems and improve existing learning rates.