JMLR
2011
13 years 7 months ago
2011
While most supervised machine learning models assume that training examples are sampled at random or adversarially, this article is concerned with models of learning from a cooper...
IPL
2011
13 years 7 months ago
2011
We provide sample complexity of the problem of learning halfspaces with monotonic noise, using the regularized least squares algorithm in the reproducing kernel Hilbert spaces (RKH...
PAMI
2007
13 years 12 months ago
2007
We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifier...
TIT
1998
14 years 2 days ago
1998
We show that if the closureof a function class F under the metric induced by some probability distribution is not convex, then the sample complexity for agnostically learning F wi...
JMLR
2002
14 years 3 days ago
2002
Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. In many of these theoretical stud...
JMLR
2006
14 years 12 days ago
2006
We study the computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded degree...
CORR
2010
Springer
14 years 16 days ago
2010
Springer
We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the -adapted-dimension, which...
CORR
2008
Springer
14 years 16 days ago
2008
Springer
Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest i...
CORR
2010
Springer
14 years 16 days ago
2010
Springer
The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in practice. In this paper, ...
ACL
1994
14 years 1 months ago
1994
This paper shows how to formally characterize language learning in a finite parameter space as a Markov structure, hnportant new language learning results follow directly: explici...