Sciweavers

148 search results - page 6 / 30
» Bounds for Linear Multi-Task Learning
Sort
View
COLT
1994
Springer
13 years 11 months ago
Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes
We examine the relationship between the VCdimension and the number of parameters of a smoothly parametrized function class. We show that the VC-dimension of such a function class ...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...
COLT
2008
Springer
13 years 9 months ago
The True Sample Complexity of Active Learning
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...
Maria-Florina Balcan, Steve Hanneke, Jennifer Wort...
ENTCS
2007
156views more  ENTCS 2007»
13 years 7 months ago
Bounded Model Checking with Parametric Data Structures
Bounded Model Checking (BMC) is a successful refutation method to detect errors in not only circuits and other binary systems but also in systems with more complex domains like ti...
Erika Ábrahám, Marc Herbstritt, Bern...
ML
2002
ACM
141views Machine Learning» more  ML 2002»
13 years 7 months ago
On the Existence of Linear Weak Learners and Applications to Boosting
We consider the existence of a linear weak learner for boosting algorithms. A weak learner for binary classification problems is required to achieve a weighted empirical error on t...
Shie Mannor, Ron Meir
COLT
2000
Springer
13 years 12 months ago
Entropy Numbers of Linear Function Classes
This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the “maximum-margin” algorithm due to Vapnik and...
Robert C. Williamson, Alex J. Smola, Bernhard Sch&...