Measuring multi-calibration
This work addresses the need for reliable scalar metrics in fairness and uncertainty quantification for machine learning practitioners, though it is incremental as it builds on existing calibration concepts.
The paper tackles the problem of measuring multi-calibration, which assesses how well probabilistic predictions are calibrated across multiple subpopulations, by proposing a new metric based on the Kuiper statistic that weights subpopulations by their signal-to-noise ratios, with ablations showing it becomes noisy without this weighting.
A suitable scalar metric can help measure multi-calibration, defined as follows. When the expected values of observed responses are equal to corresponding predicted probabilities, the probabilistic predictions are known as "perfectly calibrated." When the predicted probabilities are perfectly calibrated simultaneously across several subpopulations, the probabilistic predictions are known as "perfectly multi-calibrated." In practice, predicted probabilities are seldom perfectly multi-calibrated, so a statistic measuring the distance from perfect multi-calibration is informative. A recently proposed metric for calibration, based on the classical Kuiper statistic, is a natural basis for a new metric of multi-calibration and avoids well-known problems of metrics based on binning or kernel density estimation. The newly proposed metric weights the contributions of different subpopulations in proportion to their signal-to-noise ratios; data analyses' ablations demonstrate that the metric becomes noisy when omitting the signal-to-noise ratios from the metric. Numerical examples on benchmark data sets illustrate the new metric.