期刊
GEOSCIENTIFIC MODEL DEVELOPMENT
卷 15, 期 14, 页码 5481-5487出版社
COPERNICUS GESELLSCHAFT MBH
DOI: 10.5194/gmd-15-5481-2022
关键词
-
资金
- Hydro-terrestrial Earth Systems Testbed (HyTEST) project of the U.S. Geological Survey Integrated Water Prediction program
The root-mean-squared error (RMSE) and mean absolute error (MAE) are commonly used metrics for evaluating models, but there is confusion regarding their use and no single metric is inherently better in all cases.
The root-mean-squared error (RMSE) and mean absolute error (MAE) are widely used metrics for evaluating models. Yet, there remains enduring confusion over their use, such that a standard practice is to present both, leaving it to the reader to decide which is more relevant. In a recent reprise to the 200-year debate over their use, and give arguments for favoring one metric or the other. However, this comparison can present a false dichotomy. Neither metric is inherently better: RMSE is optimal for normal (Gaussian) errors, and MAE is optimal for Laplacian errors. When errors deviate from these distributions, other metrics are superior.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据