36 search results - page 2 / 8 » jmlr 2002 |
JMLR
2002
13 years 10 months ago
2002
We consider a finite-state Markov decision problem and establish the convergence of a special case of optimistic policy iteration that involves Monte Carlo estimation of Q-values,...
JMLR
2002
13 years 10 months ago
2002
We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out e...
JMLR
2002
13 years 10 months ago
2002
We apply a variational method to automatically determine the number of mixtures of independent components in high-dimensional datasets, in which the sources may be nonsymmetricall...
JMLR
2002
13 years 10 months ago
2002
Cross-validation is a useful and generally applicable technique often employed in machine learning, including decision tree induction. An important disadvantage of straightforward...
JMLR
2002
13 years 10 months ago
2002
One of the most important fundamental properties of Bayesian networks is the representational power, reflecting what kind of functions they can or cannot represent. In this paper,...