arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.09412stat.MLcs.LG
收藏

基于高斯过程的聚集数据多任务学习

Multi-task Learning for Aggregated Data using Gaussian Processes

University of Sheffield(谢菲尔德大学)

Fariba Yousefi, Michael Thomas Smith, Mauricio A. Álvarez

摘要:

汇总数据在流行病学和人口统计学等领域很常见。例如,人口普查数据通常是按时间段或空间分辨率(城市、区域或国家)确定的平均数。在本文中,我们提出了一种新的多任务学习模型的基础上高斯过程的联合学习的变量,已聚集在不同的输入尺度。我们的模型将每个任务表示为潜在过程实现的线性组合,这些潜在过程在每个任务的不同规模上进行集成。然后,我们能够计算不同任务之间的互协方差,无论是分析或数值。我们还允许每个任务具有潜在不同的似然模型,并提供可以以随机方式优化的变分下限,使我们的模型适用于更大的数据集。我们在一个合成示例、一个生育率数据集和一个空气污染预测应用程序中展示了该模型的示例。

英文摘要:

Aggregated data is commonplace in areas such as epidemiology and demography. For example, census data for a population is usually given as averages defined over time periods or spatial resolutions (cities, regions or countries). In this paper, we present a novel multi-task learning model based on Gaussian processes for joint learning of variables that have been aggregated at different input scales. Our model represents each task as the linear combination of the realizations of latent processes that are integrated at a different scale per task. We are then able to compute the cross-covariance between the different tasks either analytically or numerically. We also allow each task to have a potentially different likelihood model and provide a variational lower bound that can be optimised in a stochastic fashion making our model suitable for larger datasets. We show examples of the model in a synthetic example, a fertility dataset, and an air pollution prediction application.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑