事后校准方法在概率分类器中的条件分层鲁棒性分析 / Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers
1️⃣ 一句话总结
该论文通过在不同数据条件下（C1到C4）对比温度缩放和等渗回归两种校准方法，发现它们的效果并非始终如一，而是强烈依赖于具体的数据环境和评估指标，提醒用户在选择校准方法时需考虑实际应用场景的多样性。
arXiv 提交日期: 2026-07-13
Abstract - Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers
Post-hoc calibration is widely adopted to correct probability estimates from trained classifiers, yet most evaluations report aggregate performance without testing whether that performance holds across distinct operating conditions within a single dataset. We present a pre-registered, condition-stratified robustness analysis comparing temperature scaling (TEMP) and isotonic regression (ISO) across four controlled conditions (C1--C4). Four hypothesis groups are evaluated: discrimination deltas with Holm-corrected multiplicity control (H1), Brier score differences (H2), calibration slope outcomes (H3), and AUROC differences under best-condition setups (H4). TEMP-minus-ISO discrimination deltas remain small across all conditions (-0.0155 to 0.0139), with Holm-adjusted p-values of 0.9895 everywhere. TEMP Brier differences are consistently negative (C1: -0.0002 through C4: -0.0074), while ISO shows sign reversals. TEMP calibration slopes stay closer to unity in every condition (range 0.7597--0.9493) than ISO slopes (0.1364--0.2726). AUROC differences shift from near zero in C1 (-0.0004) to positive in C4 (0.0264). These results establish that in-dataset robustness is condition-dependent and metric-specific. No claim of external transportability is made.
源自 arXiv: 2607.11542