Abstract | ||
---|---|---|
This paper concerns the experimental assessment of tempering as a technique for improving Bayesian inference for C&RT models. Full Bayesian inference requires the computation of a posterior over all possible trees. Since exact computation is not possible Markov chain Monte Carlo (MCMC) methods are used to produce an approximation. C&RT posteriors have many local modes: tempering aims to prevent the Markov chain getting stuck in these modes. Our results show that a clear improvement is achieved using tempering. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1145/1102351.1102354 | ICML |
Keywords | Field | DocType |
rt posterior,rt model,bayesian inference,full bayesian inference,possible markov chain,exact computation,bayesian c,possible tree,clear improvement,markov chain,monte carlo,markov chain monte carlo | Markov chain mixing time,Variable-order Bayesian network,Bayesian inference,Markov chain Monte Carlo,Computer science,Markov chain,Artificial intelligence,Parallel tempering,Bayesian statistics,Machine learning,Bayesian probability | Conference |
ISBN | Citations | PageRank |
1-59593-180-5 | 2 | 0.39 |
References | Authors | |
3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicos Angelopoulos | 1 | 53 | 11.48 |
James Cussens | 2 | 503 | 50.29 |