JMLR
2008
13 years 11 months ago
2008
We introduce a computationally feasible, "constructive" active learning method for binary classification. The learning algorithm is initially formulated for separable cl...
JMLR
2008
13 years 11 months ago
2008
The statistical problem of estimating the effective dimension-reduction (EDR) subspace in the multi-index regression model with deterministic design and additive noise is consider...
JMLR
2008
13 years 11 months ago
2008
The max-sum classifier predicts n-tuple of labels from n-tuple of observable variables by maximizing a sum of quality functions defined over neighbouring pairs of labels and obser...
JMLR
2008
13 years 11 months ago
2008
JMLR
2008
13 years 11 months ago
2008
Harmonic analysis and diffusion on discrete data has been shown to lead to state-of-theart algorithms for machine learning tasks, especially in the context of semi-supervised and ...
JMLR
2008
13 years 11 months ago
2008
Causal reasoning is primarily concerned with what would happen to a system under external interventions. In particular, we are often interested in predicting the probability distr...
JMLR
2008
13 years 11 months ago
2008
We analyze the performance of a class of manifold-learning algorithms that find their output by minimizing a quadratic form under some normalization constraints. This class consis...
JMLR
2008
13 years 11 months ago
2008
This paper introduces a new PAC transductive error bound for classification. The method uses information from the training examples and inputs of working examples to develop a set...
JMLR
2008
13 years 11 months ago
2008
We show how a generic feature selection algorithm returning strongly relevant variables can be turned into a causal structure learning algorithm. We prove this under the Faithfuln...
