On convergence rates of mixtures of polynomial experts

Eduardo F. Mendes*, Wenxin Jiang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)3025-3051
Number of pages27
JournalNeural Computation
Volume24
Issue number11
DOIs
StatePublished - Dec 1 2012

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Fingerprint Dive into the research topics of 'On convergence rates of mixtures of polynomial experts'. Together they form a unique fingerprint.

Cite this