COLT
2008
Springer
13 years 6 months ago
2008
Springer
Inspired by longstanding lines of research in sociology and related fields, and by more recent largepopulation human subject experiments on the Internet and the Web, we initiate a...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
This paper describes an efficient reduction of the learning problem of ranking to binary classification. The reduction guarantees an average pairwise misranking regret of at most t...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We design and analyze interacting online algorithms for multitask classification that perform better than independent learners whenever the tasks are related in a certain sense. W...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
Clustering Stability methods are a family of widely used model selection techniques applied in data clustering. Their unifying theme is that an appropriate model should result in ...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
Boosting algorithms build highly accurate prediction mechanisms from a collection of lowaccuracy predictors. To do so, they employ the notion of weak-learnability. The starting po...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
In this paper, we investigate stability-based methods for cluster model selection, in particular to select the number K of clusters. The scenario under consideration is that clust...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We describe and explore a new perspective on the sample complexity of active learning. In many situations where it was generally believed that active learning does not help, we sh...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We study distribution-dependent, data-dependent, learning in the limit with adversarial disturbance. We consider an optimization-based approach to learning binary classifiers from...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We consider the question of why modern machine learning methods like support vector machines outperform earlier nonparametric techniques like kNN. Our approach investigates the lo...