中国科学院数学与系统科学研究院
(第87期)
题目一:博弈学习系统的演化与控制研究进展
摘要:博弈学习算法是构建博弈智能决策的基础与核心。本报告将介绍课题组在学习算法驱动的博弈动态系统演化与控制问题上的研究进展。具体地,我们研究了博弈学习算法的收敛性,基于不收敛的博弈动力学给出一种全新的纳什均衡求解方法,针对经典的学习算法建立了人机博弈框架下的最优(控制)策略等。这些工作可为实现大规模博弈中的智能决策建立基础。
题目二:On efficient and scalable computation of the nonparametric maximum likelihood estimator in mixture models
摘要:The nonparametric maximum likelihood estimation (NPMLE) is a classic and important method to estimate the mixture models from finite observations. In this talk, we propose an efficient and scalable semismooth Newton based augmented Lagrangian method (ALM). By carefully exploring the structure of the ALM subproblem, we show that the computational cost of the generalized Hessian (second order information) is independent of the number of grid points. Extensive numerical experiments are conducted to show the effectiveness of our approach.
时 间:2024.11.15(星期五), 10:40-12:00
地 点:南楼204会议室/腾讯会议534-8268-8299
报告会视频
注:本视频未经允许不得转载,违者将依法追究侵权法律责任。
附件下载: