通过随机子空间联合检验，用一致p值量化分类不确定性。
Conjunction Subspaces Test for Conformal and Selective Classification
- 在多个随机子空间上做显著性检验，整合结果得共识p值。
- 理论证明分类器泛化误差有界，实验证明效果优于基线方法。
- 适合需要拒判与重审的高风险决策场景，如医疗诊断。
本文提出一种新分类器，通过在不同随机子空间上整合显著性检验结果，生成用于量化分类决策不确定性的共识p值。零假设设定为测试样本在随机选取的子空间上与目标类别无关联，因此该分类问题可建模为联合假设检验。所提分类器可通过简单设定共识p值阈值，轻松部署于置信预测和选择性分类（含拒判与重审）任务。本文还提供了所提分类器的泛化误差界理论分析，并在真实数据集上进行了实证研究，验证了其有效性。
原文摘要 · Abstract (English)
In this paper, we present a new classifier, which integrates significance testing results over different random subspaces to yield consensus p-values for quantifying the uncertainty of classification decision. The null hypothesis is that the test sample has no association with the target class on a randomly chosen subspace, and hence the classification problem can be formulated as a problem of testing for the conjunction of hypotheses. The proposed classifier can be easily deployed for the purpose of conformal prediction and selective classification with reject and refine options by simply thresholding the consensus p-values. The theoretical analysis on the generalization error bound of the proposed classifier is provided and empirical studies on real data sets are conducted as well to demonstrate its effectiveness.
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。