On the coercivity condition in the learning of interacting particle systems

On the coercivity condition in the learning of interacting particle systems
复制标题

关于相互作用粒子系统学习中的矫顽力条件

DOI:
10.1142/s0219493723400038
复制
发表时间:
2020
期刊:
ArXiv
影响因子:
--
通讯作者:
F. Lu
F. Lu
中科院分区:
--
文献类型:
--
作者:
Zhongyan Li;F. Lu

文献摘要

参考文献

被引文献

相似文献

在学习相互作用粒子或代理系统的系统中,强制性条件可确保相互作用功能的可识别性,从而通过非参数回归为学习的基础提供了基础。强制性条件等同于学习中不可或缺的内核的严格积极确定性。我们表明,对于一类相互作用的函数,系统是千古的,积分内核是严格的积极确定的,因此强制性条件是正确的。
In the learning of systems of interacting particles or agents, coercivity condition ensures identifiability of the interaction functions, providing the foundation of learning by nonparametric regression. The coercivity condition is equivalent to the strictly positive definiteness of an integral kernel arising in the learning. We show that for a class of interaction functions such that the system is ergodic, the integral kernel is strictly positive definite, and hence the coercivity condition holds true.
DOI: 10.1016/j.spa.2020.10.005
发表时间: 2019-12
影响因子: 1.4
作者:
Zhongyan Li;F. Lu;M. Maggioni;Sui Tang;C. Zhang
通讯作者: Zhongyan Li;F. Lu;M. Maggioni;Sui Tang;C. Zhang
DOI: 10.1007/s43670-023-00055-9
发表时间: 2020-10
期刊: Sampling Theory, Signal Processing, and Data Analysis
影响因子: --
作者:
Jason Miller;Sui Tang;Ming Zhong;M. Maggioni
通讯作者: Jason Miller;Sui Tang;Ming Zhong;M. Maggioni
DOI: 10.1007/s10208-021-09521-z
发表时间: 2021
影响因子: 3
作者:
Lu, Fei;Maggioni, Mauro;Tang, Sui
通讯作者: Tang, Sui
从轨迹数据中非参数推断智能体系统中的相互作用规律
DOI: 10.1073/pnas.1822012116
发表时间: 2019
影响因子: 11.1
作者:
Lu, Fei;Zhong, Ming;Tang, Sui;Maggioni, Mauro
通讯作者: Maggioni, Mauro