11 search results - page 2 / 3 » Tight Sample Complexity of Large-Margin Learning |
COLT
2000
Springer
13 years 10 months ago
2000
Springer
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...
JMLR
2006
13 years 5 months ago
2006
Fast and frugal heuristics are well studied models of bounded rationality. Psychological research has proposed the take-the-best heuristic as a successful strategy in decision mak...
COLT
2003
Springer
13 years 10 months ago
2003
Springer
Abstract. We study the problem of learning partitions using equivalence constraints as input. This is a binary classification problem in the product space of pairs of datapoints. ...
ICML
2008
IEEE
14 years 6 months ago
2008
IEEE
In high-dimensional classification problems it is infeasible to include enough training samples to cover the class regions densely. Irregularities in the resulting sparse sample d...
TNN
2010
13 years 9 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...