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

Neural Computation

November 2012, Vol. 24, No. 11, Pages 3025-3051
(doi: 10.1162/NECO_a_00354)
© 2012 Massachusetts Institute of Technology
On Convergence Rates of Mixtures of Polynomial Experts
Article PDF (231.46 KB)
Abstract

In this letter, we consider a mixture-of-experts structure where m experts are mixed, with each expert being related to a polynomial regression model of order k. We study the convergence rate of the maximum likelihood estimator in terms of how fast the Hellinger distance of the estimated density converges to the true density, when the sample size n increases. The convergence rate is found to be dependent on both m and k, while certain choices of m and k are found to produce near-optimal convergence rates.