English

Detecting Underspecification with Local Ensembles

Machine Learning 2021-12-09 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1910.09573,
  title  = {Detecting Underspecification with Local Ensembles},
  author = {David Madras and James Atwood and Alex D'Amour},
  journal= {arXiv preprint arXiv:1910.09573},
  year   = {2021}
}

Comments

Published as a conference paper at ICLR 2020 under the title "Detecting Extrapolation with Local Ensembles"

R2 v1 2026-06-23T11:50:24.185Z