Accelerating Ensemble Error Bar Prediction with Single Models Fits

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Agrawal, Vidit, Zhang, Shixin, Schultz, Lane E., Morgan, Dane
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918366853201920
author Agrawal, Vidit
Zhang, Shixin
Schultz, Lane E.
Morgan, Dane
author_facet Agrawal, Vidit
Zhang, Shixin
Schultz, Lane E.
Morgan, Dane
contents 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 $A_{E}$ for traditional ensemble-based error bar prediction, and Model B, fit to data from Model $A_{E}$, to be used for predicting the values of $A_{E}$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09896
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Accelerating Ensemble Error Bar Prediction with Single Models Fits
Agrawal, Vidit
Zhang, Shixin
Schultz, Lane E.
Morgan, Dane
Machine Learning
Materials Science
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 $A_{E}$ for traditional ensemble-based error bar prediction, and Model B, fit to data from Model $A_{E}$, to be used for predicting the values of $A_{E}$ 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.
title Accelerating Ensemble Error Bar Prediction with Single Models Fits
topic Machine Learning
Materials Science
url https://arxiv.org/abs/2404.09896