Skip to content

Estimating Expected Calibration Errors

Uncertainty in probabilistic classifiers predictions is a key concern when models are used to support human decision making, in broader probabilistic pipelines or when sensitive automatic decisions have to be taken.
Studies have shown that most models are not intrinsically well calibrated, meaning that their decision scores are not consistent with posterior probabilities.
Hence being able to calibrate these models, or enforce calibration while learning them, has regained interest in recent literature.
In this context, properly assessing calibration is paramount to quantify new contributions tackling calibration.
However, there is room for improvement for commonly used metrics and evaluation of calibration could benefit from deeper analyses.
Thus this paper focuses on the empirical evaluation of calibration metrics in the context of classification.
More specifically it evaluates different estimators of the Expected Calibration Error ($ECE$), amongst which legacy estimators and some novel ones, proposed in this paper.
We build an empirical procedure to quantify the quality of these $ECE$ estimators, and use it to decide which estimator should be used in practice for different settings.

Nicolas Posocco, Antoine Bonnefoy, Estimating Expected Calibration Errors, In Proc. of the The 30th International Conference on Artificial Neural Networks, 2021.

Watch the presentation on YouTube.

Click here to access the paper.

Releated Posts

2022 Wrap Up

We got a deep dive into some of the most memorable moments of 2022.
Read More

IEEE Big Data 2022: the key takeaways

In December 2022, our research director Sabri Skhiri travelled to Osaka to attend IEEE Big Data 2022. He sums up the main trends, and shares his favourite talks and papers.
Read More