arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11770stat.MLcs.LG
收藏

纵向深核高斯过程回归

Longitudinal Deep Kernel Gaussian Process Regression

Pennsylvania State University(宾夕法尼亚州立大学)

Junjie Liang, Yanting Wu, Dongkuan Xu, Vasant Honavar

摘要:

高斯过程为从纵向数据进行预测建模提供了有吸引力的框架,即,随着时间的推移,从一组个体中进行不规则采样的稀疏观察。然而,这样的方法有两个关键的缺点:(i)他们依赖于临时的算法或昂贵的试错来选择有效的内核,(ii)他们无法处理数据中的多级相关结构。我们引入纵向深度核高斯过程回归(L-DKGPR),据我们所知,这是唯一的方法,以克服这些限制,通过完全自动化的发现复杂的多级相关结构从纵向数据。具体而言,L-DKGPR消除了对特设算法或试错的需要,使用深度内核学习的新适应,将深度神经网络的表达能力与非参数核方法的灵活性相结合。L-DKGPR有效地学习与一种新的加法内核,同时适应时变和时不变的影响的多级相关。利用隐空间诱导点和变分推断,我们得到了一个有效的训练L-DKGPR的算法。在多个基准数据集上的大量实验结果表明,L-DKGPR显著优于最先进的纵向数据分析(LDA)方法。

英文摘要:

Gaussian processes offer an attractive framework for predictive modeling from longitudinal data, i.e., irregularly sampled, sparse observations from a set of individuals over time. However, such methods have two key shortcomings: (i) They rely on ad hoc heuristics or expensive trial and error to choose the effective kernels, and (ii) They fail to handle multilevel correlation structure in the data. We introduce Longitudinal deep kernel Gaussian process regression (L-DKGPR), which to the best of our knowledge, is the only method to overcome these limitations by fully automating the discovery of complex multilevel correlation structure from longitudinal data. Specifically, L-DKGPR eliminates the need for ad hoc heuristics or trial and error using a novel adaptation of deep kernel learning that combines the expressive power of deep neural networks with the flexibility of non-parametric kernel methods. L-DKGPR effectively learns the multilevel correlation with a novel addictive kernel that simultaneously accommodates both time-varying and the time-invariant effects. We derive an efficient algorithm to train L-DKGPR using latent space inducing points and variational inference. Results of extensive experiments on several benchmark data sets demonstrate that L-DKGPR significantly outperforms the state-of-the-art longitudinal data analysis (LDA) methods.

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。

↑