用稀疏激活实现不确定性量化，自动获得置信集覆盖保证。
Sparse Activations as Conformal Predictors
- 将稀疏softmax类变换与置信预测结合，设计新非一致性评分
- 校准后使用稀疏变换生成的标签集能保持指定覆盖率
- 在图像和文本分类上比传统softmax更高效、自适应性更强
置信预测是一种无需分布假设的不确定性量化框架，将点预测替换为集合，提供边际覆盖率保证（即预测集在期望下以指定概率包含真实标签）。本文揭示了置信预测与稀疏softmax类变换（如sparsemax和γ-entmax，其中γ>1）之间的新联系，这类变换仅对部分标签分配非零概率。我们提出新的非一致性评分，使校准过程对应于常用的温度缩放方法。测试时，使用校准后的温度施加这些稀疏变换，其支持集（即非零概率标签集合）可自动继承置信预测的覆盖率保证。在计算机视觉和文本分类基准上的实验表明，该方法在覆盖率、效率和自适应性方面优于基于softmax的标准非一致性评分。
原文摘要 · Abstract (English)
Conformal prediction is a distribution-free framework for uncertainty quantification that replaces point predictions with sets, offering marginal coverage guarantees (i.e., ensuring that the prediction sets contain the true label with a specified probability, in expectation). In this paper, we uncover a novel connection between conformal prediction and sparse softmax-like transformations, such as sparsemax and $γ$-entmax (with $γ> 1$), which may assign nonzero probability only to a subset of labels. We introduce new non-conformity scores for classification that make the calibration process correspond to the widely used temperature scaling method. At test time, applying these sparse transformations with the calibrated temperature leads to a support set (i.e., the set of labels with nonzero probability) that automatically inherits the coverage guarantees of conformal prediction. Through experiments on computer vision and text classification benchmarks, we demonstrate that the proposed method achieves competitive results in terms of coverage, efficiency, and adaptiveness compared to standard non-conformity scores based on softmax.
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。