Convergence rates of the Voting Gibbs classifier, with application to Bayesian feature selection

@inproceedings{Ng2001ConvergenceRO,
  title={Convergence rates of the Voting Gibbs classifier, with application to Bayesian feature selection},
  author={Andrew Y. Ng and Michael I. Jordan},
  booktitle={ICML},
  year={2001}
}
The Gibbs classiier is a simple approximation to the Bayesian optimal classiier in which one samples from the posterior for the parameter , and then classiies using the single classiier indexed by that parameter vector. In this paper, we study the Voting Gibbs classiier, which is the extension of this scheme to the full Monte Carlo setting, in which N samples are drawn from the posterior and new inputs are classiied by voting the N resulting classiiers. We show that the error of Voting Gibbs… CONTINUE READING

Similar Papers

Loading similar papers…