提升预测效率时，模型熵会下降，新方法平衡二者关系。
Conformal Correction for Efficiency May be at Odds with Entropy
- 用约束熵的方法优化校准预测的效率
- 在多个数据集上使最先进方法效率提升最高达34.4%
- 适合关注模型可靠性与效率平衡的研究者
conformal prediction (CP) 为黑箱机器学习模型提供严格的不确定性置信集。为提升 CP 效率，提出 conformal correction 方法，通过一个感知校准的低效损失对基础模型进行微调或封装。本文通过实验和理论分析发现，CP 效率与模型预测熵之间存在权衡。为此，提出一种熵约束的 conformal correction，探索效率与熵之间的更优帕累托前沿。在计算机视觉与图数据集上的大量实验表明该方法有效：例如，在设定熵阈值条件下，可使最先进的 CP 方法效率最高提升 34.4%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。