论文标题
自动相关性确定先前的贝叶斯神经网络用于控制变量选择
An Automatic Relevance Determination Prior Bayesian Neural Network for Controlled Variable Selection
论文作者
论文摘要
我们提出了自动相关性确定先前的贝叶斯神经网络（BNN-ARD）重量L2-Norm度量，这是对模型X仿制滤波器的特征重要性统计量。我们在模拟数据和挪威风电场数据集上都显示，相对于可变选择功率和现实世界数据集中的可变选择功率和预测性能的相似特征重要性度量相比，提出的特征重要性统计量产生了统计学上的显着改进。
We present an Automatic Relevance Determination prior Bayesian Neural Network(BNN-ARD) weight l2-norm measure as a feature importance statistic for the model-x knockoff filter. We show on both simulated data and the Norwegian wind farm dataset that the proposed feature importance statistic yields statistically significant improvements relative to similar feature importance measures in both variable selection power and predictive performance on a real world dataset.
