基本信息
- 来源: arxiv
- 原始来源: https://arxiv.org/abs/2602.24230v1
- 作者: Eugène Berta, Sacha Braun, David Holzmüller, Francis Bach, Michael I. Jordan
- 分类: stat.ML
- 论文时间: 2026-02-27T17:56:52Z
- 论文 PDF: https://arxiv.org/pdf/2602.24230v1.pdf
来源摘要/节选
Calibration$\unicode{x2014}$the problem of ensuring that predicted probabilities align with observed class frequencies$\unicode{x2014}$is a basic desideratum for reliable prediction with machine learning systems. Calibration error is traditionally assessed via a divergence function, using the expected divergence between predictions and empirical frequencies. Accurately estimating this quantity is challenging, especially in the multiclass setting. Here, we show how to extend a recent variational framework for estimating calibration errors beyond divergences induced induced by proper losses, to cover a broad class of calibration errors induced by $L_p$ divergences. Our method can separate over- and under-confidence and, unlike non-variational approaches, avoids overestimation. We provide extensive experiments and integrate our code in the open-source package probmetrics (https://github.com/dholzmueller/probmetrics) for evaluating calibration errors.
来源说明
当前只保存了官方论文摘要，不代表论文全文。请以原始来源为准。
本页只呈现已做哈希绑定的来源证据，不包含基于旧正文或缺失原文的扩展推断。