arXiv：cs.LG· Ivan Lerner, Anita Burgun, Francis Bach·· 3 小时前
StructGP：面向临床时间序列的谱结构学习
Spectral structure learning for clinical time series
AI 导读
研究者为临床多变量时间序列提出结构学习算法，假设数据来自 StructGP——一种多任务平稳高斯过程，用有向无环图编码时间序列间的有序条件关系，并采用可微无环性定义的 NOTEARS 算法变体通过连续优化恢复图结构。
正文
Abstract:We develop and evaluate a structure learning algorithm for clinical time series. Clinical time series are multivariate time series observed in multiple patients and irregularly sampled, challenging existing structure learning algorithms. We assume that our times series are realizations of StructGP, a k-dimensional multi-output or multi-task stationary Gaussian process (GP), with independent patients sharing the same covariance function. StructGP encodes ordered conditional relations between time series, represented in a directed acyclic graph. We implement an adapted NOTEARS algorithm, which based on a differentiable definition of acyclicity, recovers the graph by solving a series of continuous optimization problems. Simulation results show that up to mean degree 3 and 20 tasks, we reach a median recall of 0.93% [IQR, 0.86, 0.97] while keeping a median precision of 0.71% [0.57-0.84], for recovering directed edges. We further show that the regularization path is key to identifying the graph. With StructGP, we proposed a model of time series dependencies, that flexibly adapt to different time series regularity, while enabling us to learn these dependencies from observations.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2502.11680 [cs.LG] |
| (or arXiv:2502.11680v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2502.11680 arXiv-issued DOI via DataCite |
Submission history
From: Ivan Lerner [view email]
[v1]
Mon, 17 Feb 2025 11:13:39 UTC (452 KB)
[v2]
Wed, 14 Oct 2026 09:09:19 UTC (197 KB)
来源：arXiv：cs.LG · arxiv.org