中文摘要：

在计算机试验中,复杂现象的仿真拥有数目庞大的输入变量,因此,筛选出对输出影响重要的输入变量是至关重要的。我们通过Jeffreys非信息超先验,提出了一种新的贝叶斯变量选择算法。不同于计算机试验中存在的变量选择算法,我们的方法不需要调节控制稀疏性的超参数。新的变量选择方法通过EM（expectation-maximization）算法求解,试验结果表明,我们的方法不仅取得了理想的效果,而且大大地减少了计算的负担。

英文摘要：

In computer experiments,simulation of complex phenomenon requires a large number of inputs and identifying the inputs which most impact the outputs is of crucial importance.A novel algorithm of Bayesian variable selection was proposed for computer experiments via a Jeffreys＇ noninformative super prior.Different from existed algorithms of variable selection in computer experiments,the proposed algorithm has no necessity to choose the sparseness-controlling hyperparameters.Implementation was carried out by an EM（expectation-maximization） algorithm and experimental results demonstrate that the new approach not only yields state-of-art performance but also has low computational cost.