报告人：金卓（澳大利亚Macquarie大学）

邀请人：吴付科

报告时间：2023年7月13日（星期四）10:30-11:30

报告地点：科技楼南楼711室

报告题目：Markov chain approximation-based deep learning in stochastic control

报告摘要：We will introduce a series of deep learning approaches and its application in insurance decision making problems, where decision makers are subject to the randomness of the financial ruin time to terminate the control processes. Markov chain approximation-based iterative deep learning algorithms are developed to study this type of infinite-horizon optimal control problems. The optimal controls are approximated as deep neural networks. The framework of Markov chain approximation plays a key role in building the iterative equations and initialization of the algorithm. Optimal parameters of neural networks are then obtained iteratively.

报告人简介：金卓教授，澳大利亚麦考瑞大学精算中心教授，2005年和2007毕业于华中科技大学数学系应用数学专业，分别获理学学士和硕士学位，2011年毕业于美国韦恩州立大学数学系数学专业，获哲学博士学位。2011年9月至今在澳大利亚墨尔本大学经济系精算中心工作。研究方向为随机最优控制，随机系统的数值方法，精算学，数理金融。在国际期刊发表60余篇论文，期刊包括Insurance Mathematics and Economics, European Journal of Operational Research, SIAM Journal on Control and Optimization, Automatica, ASTIN: Bulletin, Scandinavian Actuarial Journal.