时 间：2022年10月19日13：30-14：00
地 点：腾讯会议ID：811-916-088
报告人：张思亮 助理教授
主持人：唐炎林 研究员
摘 要：
Latent variable models have been playing a central role in psychometrics and related fields. In many modern applications, the inference based on latent variable models involves one or several of the following features: (1) the presence of many latent variables, (2) the observed and latent variables being continuous, discrete, or a combination of both, (3) constraints on parameters, and (4) penalties on parameters to impose model parsimony. The estimation often involves maximizing an objective function based on a marginal likelihood/pseudo-likelihood, possibly with constraints and/or penalties on parameters. Solving this optimization problem is highly non-trivial, due to the complexities brought by the features mentioned above. Although several efficient algorithms have been proposed, there lacks a unified computational framework that takes all these features into account. We fill the gap in this study. Specifically, we provide a unified formulation for the optimization problem and then propose a quasi-Newton stochastic proximal algorithm. Theoretical properties of the proposed algorithms are established. Simulation studies show the computational efficiency and robustness under various latent variable model estimation settings.
报告人简介：
张思亮现任华东师范大学统计学院助理教授。复旦大学上海数学中心和美国哥伦比亚大学统计系联合培养博士，随后，他在英国伦敦政治经济学院(LSE)统计系从事博士后研究。他的主要研究方向为 大规模项目反应理论，潜变量建模与统计计算，多元层次建模及其在社会科学中的应用。主要研究内容发表在Psychometrika, Journal of the American Statistical Association, Annals of Applied Statistics等期刊. 曾为Psychometrika, Statistics and Computing, Structural Equation Modeling: A Multidisciplinary Journal等审稿人.