We model time-varying network data as realizations from multivariate Gaussian distributions with precision matrices that change over time. To facilitate parameter estimation, we require not only that each precision matrix at any given time point be sparse, but also that precision matrices at neighboring time points be similar. We accomplish this with two different algorithms, by generalizing the elastic net and the fused LASSO, respectively. Our main focuses are efficient computational algorithms and convenient degree-of-freedom formulae for choosing tuning parameters. We illustrate our methods with two simulation studies. By applying them to an fMRI data set, we also detect some interesting differences in brain connectivity between healthy individuals and ADHD patients.
A comprehensive guideline for regularization-path variable selection in high-dimensional Gaussian linear regression
Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);INRAE(法国国家农业、食品和环境研究所);Nantes Université(南特大学);CEA(法国原子能和替代能源委员会);Institut de Biologie Intégrative de la Cellule (UMR 9198)(整合细胞生物学研究所 (UMR 9198));Université Evry(埃夫里大学);Université Paris Cité(巴黎西岱大学);AgroParisTech(巴黎农艺学院)
AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow
Big Data Lab, Baidu Research(百度研究院大数据实验室);School of Artificial Intelligence and Automation Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)
Manifold-constrained Gaussian process inference for time-varying parameters in dynamic systems
在生物医学研究和其他科学领域中,对动态系统建模时,常微分方程(ODE)中的参数识别是一项重要且具有挑战性的任务,特别是在存在时变参数的情况下。本文提出了一种快速、准确的时变MAnifold-constrained高斯过程推断方法TVMAGI(Time-Varying MAnifold-constrained Gaussian process Inference),利用噪声和稀疏观测数据同时估计常微分方程中的时常数和时变参数。TVMAGI在系统元件的时间序列以及时变参数上施加高斯过程模型,并限制导数过程以满足ODE条件。因此,TVMAGI完全绕过数值积分,并实现了计算时间的大幅节省。通过将ODE结构通过多种约束,TVMAGI享有贝叶斯范式下的原则性统计结构,这进一步使其能够处理系统与缺失数据或未观察到的组件。高斯过程先验也解决了常微分方程中时变参数的可辨识性问题。与现有的方法不同,TVMAGI可以应用于一般的非线性系统,而无需特定的结构假设。三个仿真例子,包括一个传染病房室模型,以说明我们的方法的鲁棒性和效率相比,数值积分和贝叶斯滤波方法。