arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.02704cs.LG
收藏

符合性校正以提高效率可能与熵相矛盾

Conformal Correction for Efficiency May be at Odds with Entropy

State Key Laboratory for Novel Software Technology, Nanjing University, China(新型软件技术国家重点实验室,南京大学,中国);School of Computing and Mathematical Sciences, Birkbeck, University of London(计算与数学科学学院,伯克贝克大学,伦敦)

Senrong Xu, Tianyu Wang, Zenan Li, Yuan Yao, Taolue Chen, Feng Xu, Xiaoxing Ma

AI总结:

本文提出一种熵约束的符合性校正方法,以在提升CP效率的同时平衡模型预测熵,实验表明其能显著提高现有CP方法的效率。

摘要:

符合性预测(CP)提供了一个全面的框架,用于为黑盒机器学习模型生成统计上严谨的不确定性集。为了进一步提高CP的效率,提出了一种符合性校正方法,通过使用一种符合性感知的低效损失,对基础模型进行微调或包装,增加额外模块。在本工作中,我们通过实证和理论分析,识别了CP效率与模型预测熵之间的权衡。随后,我们提出了一种熵约束的符合性校正方法,探索了效率与熵之间的更好的帕累托最优解。在计算机视觉和图数据集上的大量实验结果证明了所提方法的有效性。例如,它可以在给定熵阈值的情况下,将最先进的CP方法的效率提高多达34.4%。

英文摘要:

Conformal prediction (CP) provides a comprehensive framework to produce statistically rigorous uncertainty sets for black-box machine learning models. To further improve the efficiency of CP, conformal correction is proposed to fine-tune or wrap the base model with an extra module using a conformal-aware inefficiency loss. In this work, we empirically and theoretically identify a trade-off between the CP efficiency and the entropy of model prediction. We then propose an entropy-constrained conformal correction method, exploring a better Pareto optimum between efficiency and entropy. Extensive experimental results on both computer vision and graph datasets demonstrate the efficacy of the proposed method. For instance, it can significantly improve the efficiency of state-of-the-art CP methods by up to 34.4%, given an entropy threshold.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑