The nature of statistical learning theory
The nature of statistical learning theory
Machine Learning
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Model Selection and Error Estimation
Machine Learning
The Journal of Machine Learning Research
Rademacher and gaussian complexities: risk bounds and structural results
The Journal of Machine Learning Research
Trading convexity for scalability
ICML '06 Proceedings of the 23rd international conference on Machine learning
An Experimental Study on Pedestrian Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
An empirical evaluation of deep architectures on problems with many factors of variation
Proceedings of the 24th international conference on Machine learning
Maximal Discrepancy for Support Vector Machines
Neurocomputing
| Hi-index | 0.10 |
We derive in this work new upper bounds for estimating the generalization error of kernel classifiers, that is the misclassification rate that the models will perform on new and previously unseen data. Though this paper is more targeted towards the error estimation topic, the generalization error can be obviously exploited, in practice, for model selection purposes as well. The derived bounds are based on Rademacher complexity and result to be particularly useful when a set of unlabeled samples are available, in addition to the (labeled) training examples: we will show that, by exploiting further unlabeled patterns, the confidence term of the conventional Rademacher complexity bound can be reduced by a factor of three. Moreover, the availability of unlabeled examples allows also to obtain further improvements by building localized versions of the hypothesis class containing the optimal classifier.