用高斯过程量化预测的可信度，判断是否基于已有数据。
Trustworthy Prediction with Gaussian Process Knowledge Scores
- 提出知识得分衡量高斯过程预测受历史数据影响程度。
- 得分越接近1，预测越可靠，能提前识别准确预测。
- 适合需要可信预测的场景，如异常检测和缺失数据填补。
概率模型常用于未观测数据区域进行预测，但难以判断这些预测是否真正基于已有数据。本文为高斯过程回归（GPR）模型提出一种知识得分，量化观测数据对预测不确定性降低的程度。该得分可解释且自然介于0到1之间。多个实验表明，知识得分能有效预判GPR预测的准确性，并在异常检测、外推和缺失数据插补等任务中提升性能。项目源代码已公开于https://github.com/KurtButler/GP-knowledge。
原文摘要 · Abstract (English)
Probabilistic models are often used to make predictions in regions of the data space where no observations are available, but it is not always clear whether such predictions are well-informed by previously seen data. In this paper, we propose a knowledge score for predictions from Gaussian process regression (GPR) models that quantifies the extent to which observing data have reduced our uncertainty about a prediction. The knowledge score is interpretable and naturally bounded between 0 and 1. We demonstrate in several experiments that the knowledge score can anticipate when predictions from a GPR model are accurate, and that this anticipation improves performance in tasks such as anomaly detection, extrapolation, and missing data imputation. Source code for this project is available online at https://github.com/KurtButler/GP-knowledge.
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。