← Back to all news
arXiv Machine Learning By Eug\`ene Berta, Sacha Braun, Francis Bach, Michael I. Jordan, David Holzm\"uller

V-ECE: Estimating General Expected Calibration Errors

Read the original on arXiv Machine Learning →

The paper introduces V-ECE, a variational estimator for general Expected Calibration Errors (ECE) that avoids binning and works with any convex divergence, including Lp distances. By using prediction‑dependent proper scores and a residual‑fitted temperature scaling via gradient boosting, V‑ECE provides a lower‑bound estimate of true calibration error. Experiments on semi‑synthetic benchmarks show V‑ECE outperforms existing binary and multiclass estimators, with additional theoretical insights on bias and confidence estimation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 14

A Ranking Approach for Measuring Calibration

The paper introduces rankECE, a new metric for assessing calibration error in predictive models. Unlike the widely used Expected Calibration Error (ECE), rankECE compares predictions with neighboring probability values, offering theoretical guarantees and empirical evidence that it better approximates ECE than traditional binned methods.

By Anirban Chatterjee, Rina Foygel Barber
More like this →
arXiv Machine Learning
2d ago

Fragility-aware Classification for Risk Characterization and Robust Learning

The paper introduces the Fragility Index (FI), a new performance metric that measures the tail risk of confident misclassifications in classification models. FI is framed within a robust satisficing framework to assess classifier sensitivity under distributional uncertainty, and the authors develop a surrogate-based training method with provable bounds linking training fragility to ranking-error FI. The approach is extended to common loss functions and includes an FI-based regularizer for deep neural networks, with empirical studies on medical diagnosis tasks showing that FI reveals risk not captured by accuracy or AUC and leads to models with lower operational costs in a human–AI diagnostic workflow.

By Zheng Cui, Daniel Zhuoyu Long, Jin Qi, Chen Yang, Ruohan Zhan
safety
More like this →