Nonparametric estimation via empirical risk minimization
Lugosi, G.
Zeger, K.
Dept. of Math. & Comput. Sci., Tech. Univ. Budapest;
This paper appears in: Information Theory, IEEE Transactions on
Publication Date: May 1995
Volume: 41,
Issue: 3
On page(s): 677-687
ISSN: 0018-9448
References Cited: 78
CODEN: IETTAW
INSPEC Accession Number: 4959136
Digital Object Identifier: 10.1109/18.382014
Current Version Published: 2002-08-06
Abstract
A general notion of universal consistency of nonparametric
estimators is introduced that applies to regression estimation,
conditional median estimation, curve fitting, pattern recognition, and
learning concepts. General methods for proving consistency of estimators
based on minimizing the empirical error are shown. In particular,
distribution-free almost sure consistency of neural network estimates
and generalized linear estimators is established
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
