# Accelerating Ensemble Error Bar Prediction with Single Models Fits

arXiv: https://arxiv.org/abs/2404.09896 · HTML: https://mlsanity.com/paper/2404.09896/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 15 Apr 2024.

## Builds on (most cited first, 5 of 5)

- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Uncertainty Quantification Using Neural Networks for Molecular Property Prediction](https://mlsanity.com/paper/2005.10036/) (2020)
- [Machine learning modeling of superconducting critical temperature](https://mlsanity.com/paper/1709.02727/) (2017)
- [A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations](https://mlsanity.com/paper/2108.08882/) (2021)

## Abstract (arXiv)

Ensemble models can be used to estimate prediction uncertainties in machine learning models. However, an ensemble of N models is approximately N times more computationally demanding compared to a single model when it is used for inference. In this work, we explore fitting a single model to predicted ensemble error bar data, which allows us to estimate uncertainties without the need for a full ensemble. Our approach is based on three models: Model A for predictive accuracy, Model AE for traditional ensemble-based error bar prediction, and Model B, fit to data from Model AE, to be used for predicting the values of AE but with only one model evaluation. Model B leverages synthetic data augmentation to estimate error bars efficiently. This approach offers a highly flexible method of uncertainty quantification that can approximate that of ensemble methods but only requires a single extra model evaluation over Model A during inference. We assess this approach on a set of problems in materials science.