Detecting Underspecification with Local Ensembles

ICLR(2021)

引用 19|浏览1
暂无评分
摘要
We present local ensembles, a method for detecting underspecification -- when many possible predictors are consistent with the training data and model class -- at test time in a pre-trained model. Our method uses local second-order information to approximate the variance of predictions across an ensemble of models from the same class. We compute this approximation by estimating the norm of the component of a test point's gradient that aligns with the low-curvature directions of the Hessian, and provide a tractable method for estimating this quantity. Experimentally, we show that our method is capable of detecting when a pre-trained model is underspecified on test data, with applications to out-of-distribution detection, detecting spurious correlates, and active learning.
更多
查看译文
关键词
extrapolation, reliability, influence functions, laplace approximation, ensembles, Rashomon set
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要