7 search results - page 1 / 2 » Mistake Bounds for Maximum Entropy Discrimination |
NIPS
2004
13 years 6 months ago
2004
We establish a mistake bound for an ensemble method for classification based on maximizing the entropy of voting weights subject to margin constraints. The bound is the same as a ...
ICML
2001
IEEE
14 years 5 months ago
2001
IEEE
We present an improved bound on the difference between training and test errors for voting classifiers. This improved averaging bound provides a theoretical justification for popu...
UAI
2004
13 years 6 months ago
2004
Exponential models of distributions are widely used in machine learning for classification and modelling. It is well known that they can be interpreted as maximum entropy models u...
JMLR
2011
12 years 11 months ago
2011
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
NIPS
2004
2004
Class-size Independent Generalization Analsysis of Some Discriminative Multi-Category Classification
13 years 6 months ago
We consider the problem of deriving class-size independent generalization bounds for some regularized discriminative multi-category classification methods. In particular, we obtai...