提出新校准方法，让模型预测更可信
Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax
- 用带上下界的softmax函数约束输出概率
- 在4个真实数据集上显著降低校准误差
- 适合需要可靠置信度的部署场景
许多研究发现，现代神经网络虽准确率高，但输出概率校准不佳，校准成为关键实际问题。本文提出概率边界（PB）这一新型后处理校准方法，通过学习输出概率的上下界来缓解低估和高估问题。为实现PB，我们引入盒约束softmax（BCSoftmax），这是对Softmax的推广，能显式约束输出概率的上下界。尽管BCSoftmax被形式化为盒约束优化问题，我们设计了精确高效的计算算法。我们还为PB提供了理论保证，并提出了两种变体。在四个真实世界数据集上的实验表明，该方法持续降低了校准误差。Python实现已开源：https://github.com/neonnnnn/torchbcsoftmax。
原文摘要 · Abstract (English)
Many studies have observed that modern neural networks achieve high accuracy while producing poorly calibrated probabilities, making calibration a critical practical issue. In this work, we propose probability bounding (PB), a novel post-hoc calibration method that mitigates both underconfidence and overconfidence by learning lower and upper bounds on the output probabilities. To implement PB, we introduce the box-constrained softmax (BCSoftmax) function, a generalization of Softmax that explicitly enforces lower and upper bounds on the output probabilities. While BCSoftmax is formulated as the solution to a box-constrained optimization problem, we develop an exact and efficient algorithm for computing BCSoftmax. We further provide theoretical guarantees for PB and introduce two variants of PB. We demonstrate the effectiveness of our methods experimentally on four real-world datasets, consistently reducing calibration errors. Our Python implementation is available at https://github.com/neonnnnn/torchbcsoftmax.
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。