Information-Based Calibration of Uncertainty Quantification in Product-of-Experts Gaussian Process Models
专家乘积高斯过程模型中不确定性量化的基于信息的校准
机构 * University College London(伦敦大学学院) ; The University of Manchester(曼彻斯特大学)
AI总结 该研究针对专家乘积高斯过程模型的后验方差高估问题,提出基于信息校准的GP-pro-c模型,在降低计算复杂度的同时,使NLL平均降2.3%、ENCE平均降12.0%,可用于高维大规模数据的贝叶斯优化。
Comments Published in the Journal of Artificial Intelligence Research, Volume 86 (2026)
Journal ref Journal of Artificial Intelligence Research, Vol. 86 (2026)