On normal approximation rates for certain sums of dependent random variables
Journal of Computational and Applied Mathematics
On the exponential value of labeled samples
Pattern Recognition Letters
Learning from a mixture of labeled and unlabeled examples with parametric side information
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Face detection by aggregated Bayesian network classifiers
Pattern Recognition Letters - In memory of Professor E.S. Gelsema
RCV1: A New Benchmark Collection for Text Categorization Research
The Journal of Machine Learning Research
Boosting for transfer learning
Proceedings of the 24th international conference on Machine learning
On the Consistency of Multiclass Classification Methods
The Journal of Machine Learning Research
Introduction to Semi-Supervised Learning
Introduction to Semi-Supervised Learning
Estimating Labels from Label Proportions
The Journal of Machine Learning Research
Unsupervised Supervised Learning I: Estimating Classification and Regression Errors without Labels
The Journal of Machine Learning Research
IEEE Transactions on Information Theory - Part 2
| Hi-index | 0.00 |
Many popular linear classifiers, such as logistic regression, boosting, or SVM, are trained by optimizing a margin-based risk function. Traditionally, these risk functions are computed based on a labeled data set. We develop a novel technique for estimating such risks using only unlabeled data and the marginal label distribution. We prove that the proposed risk estimator is consistent on high-dimensional data sets and demonstrate it on synthetic and real-world data. In particular, we show how the estimate is used for evaluating classifiers in transfer learning, and for training classifiers with no labeled data whatsoever.