推论
计算机科学
机器学习
分位数
统计推断
人工智能
置信区间
基准推理
预测区间
逻辑回归
数据挖掘
频数推理
统计
数学
贝叶斯推理
贝叶斯概率
作者
Anastasios N. Angelopoulos,Stephen Bates,Clara Fannjiang,Michael I. Jordan,Tijana Zrnic
出处
期刊:Science
[American Association for the Advancement of Science (AAAS)]
日期:2023-11-09
卷期号:382 (6671): 669-674
被引量:22
标识
DOI:10.1126/science.adi6000
摘要
Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system. The framework yields simple algorithms for computing provably valid confidence intervals for quantities such as means, quantiles, and linear and logistic regression coefficients without making any assumptions about the machine-learning algorithm that supplies the predictions. Furthermore, more accurate predictions translate to smaller confidence intervals. Prediction-powered inference could enable researchers to draw valid and more data-efficient conclusions using machine learning. The benefits of prediction-powered inference were demonstrated with datasets from proteomics, astronomy, genomics, remote sensing, census analysis, and ecology.
科研通智能强力驱动
Strongly Powered by AbleSci AI