English

Sample-based Uncertainty Quantification with a Single Deterministic Neural Network

Machine Learning 2023-07-06 v2

Abstract

Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) method is one of fundamental challenges in machine learning. Previously, a UQ method called DISCO Nets has been proposed (Bouchacourt et al., 2016), which trains a neural network by minimizing the energy score. In this method, a random noise vector in R10100\mathbb{R}^{10\text{--}100} is concatenated with the original input vector in order to produce a diverse ensemble forecast despite using a single neural network. While this method has shown promising performance on a hand pose estimation task in computer vision, it remained unexplored whether this method works as nicely for regression on tabular data, and how it competes with more recent advanced UQ methods such as NGBoost. In this paper, we propose an improved neural architecture of DISCO Nets that admits faster and more stable training while only using a compact noise vector of dimension O(1)\sim \mathcal{O}(1). We benchmark this approach on miscellaneous real-world tabular datasets and confirm that it is competitive with or even superior to standard UQ baselines. Moreover we observe that it exhibits better point forecast performance than a neural network of the same size trained with the conventional mean squared error. As another advantage of the proposed method, we show that local feature importance computation methods such as SHAP can be easily applied to any subregion of the predictive distribution. A new elementary proof for the validity of using the energy score to learn predictive distributions is also provided.

Keywords

Cite

@article{arxiv.2209.08418,
  title  = {Sample-based Uncertainty Quantification with a Single Deterministic Neural Network},
  author = {Takuya Kanazawa and Chetan Gupta},
  journal= {arXiv preprint arXiv:2209.08418},
  year   = {2023}
}

Comments

16 pages, 17 figures, 2 tables. Accepted by the 14th International Conference on Neural Computation Theory and Applications (NCTA 2022) held as part of IJCCI 2022, October 24-26, 2022, Valletta, Malta

R2 v1 2026-06-28T01:30:45.449Z