威斯康星大学张春明教授学术报告

报告题目：New structure learning method for multivariate point process data

报告人：张春明,威斯康辛大学麦迪逊分校统计学教授

邀请人：冶继民教授

报告时间：2022年7月16号上午8:30-10：00

报告平台：Zoom，link：https://uwmadison.zoom.us/j/91657626326?pwd=RzdNZnFsQmwraEdVY3N2QjZPbWRCUT09

报告人简介：

张春明，美国威斯康星大学国际著名统计学教授，统计学四大顶级期刊之一Annals of Statistics的前副主编、Journal of the American Statistical Association的的现任副主编。在统计学四大顶级期刊发表论文10余篇，主要研究领域有：Statistical learning & data mining；Statistical methods with applications to imagingneuroinformatics and bioinformatics；Multiple testing; large-scale simultaneous inference and applications；Statistical methods in financial econometrics；Non- and semi-parametric estimation & inference；Functional & longitudinal data analysis.

报告摘要：

Motivated from inferring neural connectivity from the ensemble neural spike train data, this work attempts to learn the network graph structure among nodes in a large Poisson-type network, underlying a wide array of multivariate point process data. A novel continuous-time stochastic modeling of the intensity process is developed. This talk will present a new optimization algorithm with convergence analysis and statistical properties of the proposed structure learning estimator for graph parameters relevant to mining the causal relation among nodes. Numerical studies on both simulated and real-world data demonstrate the practical utility of our proposed method.