用双层优化提升神经网络置信度准确性，让预测更可信。
Exploring the Potential of Bilevel Optimization for Calibrating Neural Networks
- 通过双层优化框架，分层优化模型参数与置信度校准。
- 在多个数据集上降低校准误差，同时保持原有准确率。
- 适合需要可靠置信度的高风险决策场景如医疗、自动驾驶。
处理不确定性对智能系统可靠决策至关重要。现代神经网络普遍存在校准不足问题，导致预测置信度难以使用。本文探索通过双层优化框架改进置信度估计与模型校准，提出一种自校准的双层神经网络训练方法。在Blobs、Spirals等模拟数据集及血液酒精浓度（BAC）仿真数据集上验证，该方法相比广泛使用的等距回归策略，显著降低校准误差，同时保持模型精度不变。
原文摘要 · Abstract (English)
Handling uncertainty is critical for ensuring reliable decision-making in intelligent systems. Modern neural networks are known to be poorly calibrated, resulting in predicted confidence scores that are difficult to use. This article explores improving confidence estimation and calibration through the application of bilevel optimization, a framework designed to solve hierarchical problems with interdependent optimization levels. A self-calibrating bilevel neural-network training approach is introduced to improve a model's predicted confidence scores. The effectiveness of the proposed framework is analyzed using toy datasets, such as Blobs and Spirals, as well as more practical simulated datasets, such as Blood Alcohol Concentration (BAC). It is compared with a well-known and widely used calibration strategy, isotonic regression. The reported experimental results reveal that the proposed bilevel optimization approach reduces the calibration error while preserving accuracy.
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。