We establish stability of random forests under the mild condition that the squared response ($Y^2$) does not have a heavy tail. In particular, our analysis holds for the practical version of random forests that is implemented in popular packages like \texttt{randomForest} in \texttt{R}. Empirical results show that stability may persist even beyond our assumption and hold for heavy-tailed $Y^2$. Using the stability property, we prove a non-asymptotic lower bound for the coverage probability of prediction intervals constructed from the out-of-bag error of random forests. With another mild condition that is typically satisfied when $Y$ is continuous, we also establish a complementary upper bound, which can be similarly established for the jackknife prediction interval constructed from an arbitrary stable algorithm. We also discuss the asymptotic coverage probability under assumptions weaker than those considered in previous literature. Our work implies that random forests, with its stability property, is an effective machine learning method that can provide not only satisfactory point prediction but also justified interval prediction at almost no extra computational cost.

We study the Bayesian model averaging approach to learning Bayesian network structures (DAGs) from data. We develop new algorithms including the first algorithm that is able to efficiently sample DAGs of a moderate size (with up to about 25 variables) according to the exact structure posterior. The DAG samples can then be used to construct estimators for the posterior of any feature. We theoretically prove good properties of our estimators and empirically show that our estimators considerably outperform the estimators from the previous state- of-the-art methods.

We study the problem of statistical model checking of probabilistic systems for PCTL unbounded until property PJoinp(Æ1UÆ2) (where Join |X| {<, d, >, e}) using the computation of P d 0(Æ1UÆ2). The approach is first proposed by Sen et al. in CAV'05 but their approach suffers from two drawbacks. Firstly, the computation of Pd0Æ1UÆ2) requires for its validity, a user-specified input parameter ´2 which the user is unlikely to correctly provide. Secondly, the validity of computation of Pd0Æ1UÆ2) is limited only to probabilistic models that do not contain loops. We present a new technique which addresses both problems described above. Essentially our technique transforms the hypothesis test for the unbounded until property in the original model into a new equivalent hypothesis test for bounded until property in our modified model. We empirically show the effectiveness of our technique and compare our results with those using the method proposed by Sen et al.