Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE)
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908536257118208 |
|---|---|
| author | Pavlovic, Maja |
| author_facet | Pavlovic, Maja |
| contents | To be considered reliable, a model must be calibrated so that its confidence in each decision closely reflects its true outcome. In this blogpost we'll take a look at the most commonly used definition for calibration and then dive into a frequently used evaluation measure for model calibration. We'll then cover some of the drawbacks of this measure and how these surfaced the need for additional notions of calibration, which require their own new evaluation measures. This post is not intended to be an in-depth dissection of all works on calibration, nor does it focus on how to calibrate models. Instead, it is meant to provide a gentle introduction to the different notions and their evaluation measures as well as to re-highlight some issues with a measure that is still widely used to evaluate calibration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19047 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE) Pavlovic, Maja Methodology Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning To be considered reliable, a model must be calibrated so that its confidence in each decision closely reflects its true outcome. In this blogpost we'll take a look at the most commonly used definition for calibration and then dive into a frequently used evaluation measure for model calibration. We'll then cover some of the drawbacks of this measure and how these surfaced the need for additional notions of calibration, which require their own new evaluation measures. This post is not intended to be an in-depth dissection of all works on calibration, nor does it focus on how to calibrate models. Instead, it is meant to provide a gentle introduction to the different notions and their evaluation measures as well as to re-highlight some issues with a measure that is still widely used to evaluate calibration. |
| title | Understanding Model Calibration -- A gentle introduction and visual exploration of calibration and the expected calibration error (ECE) |
| topic | Methodology Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.19047 |