1435 search results - page 3 / 287 » Generalization Error Bounds Using Unlabeled Data |
ML
2002
ACM
13 years 5 months ago
2002
ACM
We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea ...
TNN
2010
13 years 22 days ago
2010
Abstract--A crucial issue in designing learning machines is to select the correct model parameters. When the number of available samples is small, theoretical sample-based generali...
3DIM
2003
IEEE
13 years 11 months ago
2003
IEEE
The Cramer-Rao error bound provides a fundamental limit on the expected performance of a statistical estimator. The error bound depends on the general properties of the system, bu...
RC
2007
13 years 5 months ago
2007
This paper develops easily computed, tight bounds on Generalized Linear Predictors and instrumental variable estimators when outcome data are partially identi…ed. A salient exam...
COLT
2001
Springer
13 years 10 months ago
2001
Springer
We consider geometric conditions on a labeled data set which guarantee that boosting algorithms work well when linear classifiers are used as weak learners. We start by providing ...