Beyond Intuition, a Framework for Applying GPs to Real-World Data
University of Cambridge(剑桥大学);British Antarctic Survey(英国南极调查局);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);California Institute of Technology(加州理工学院);Aalto University(阿尔托大学)
Kenza Tazi, Jihao Andreas Lin, Ross Viljoen, Alex Gardner, ST John, Hong Ge, Richard E. Turner
备注:
Accepted at the ICML Workshop on Structured Probabilistic Inference and Generative Modelling (2023)
本文提出一个判断 GP 适用性并规范建模流程的框架,强调核设计与可扩展性,且在冰川高程变化案例中提升了测试精度。
摘要:
Gaussian Processes(GPs,高斯过程)为在小型、结构化且相关的数据集上进行回归提供了一种有吸引力的方法。然而,其部署受到计算成本以及在简单低维数据集之外如何应用 GPs 的指导有限的阻碍。我们提出一个框架,用于识别 GPs 对给定问题的适用性,以及如何建立稳健且规范良好的 GP 模型。这些指南将经验丰富的 GP 从业者的决策形式化,重点强调核设计和计算可扩展性选项。随后,该框架被应用于冰川高程变化的案例研究,并在测试时获得了更准确的结果。
英文摘要:
Gaussian Processes (GPs) offer an attractive method for regression over small, structured and correlated datasets. However, their deployment is hindered by computational costs and limited guidelines on how to apply GPs beyond simple low-dimensional datasets. We propose a framework to identify the suitability of GPs to a given problem and how to set up a robust and well-specified GP model. The guidelines formalise the decisions of experienced GP practitioners, with an emphasis on kernel design and options for computational scalability. The framework is then applied to a case study of glacier elevation change yielding more accurate results at test time.
Scalable marginalization of correlated latent variables with applications to learning particle interaction kernels
Department of Statistics and Applied Probability, University of California, Santa Barbara(加州大学圣塔芭芭拉分校统计与应用概率系);Department of Mathematics, University of California, Santa Barbara(加州大学圣塔芭芭拉分校数学系)
Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks
Next Generation Defence Multidisciplinary Technology Research Center, Pohang University of Science and Technology(下一代国防多学科技术研究中心,POSTECH大学);Department of Electrical Engineering, Pohang University of Science and Technology(电气工程系,POSTECH大学)