题目：On Robust Deep Learning for Stochastic Control Problems in Financial Mathematics,a Mathematical and a Machine Learning Perspective

报告人：Prof.dr.ir C.W. Oosterlee （Utecht University）

地点：致远楼101室

时间：2024年10月18日 14:00-15:00

摘要：In this presentation, we will present two perspectives on deep learning for optimal stochastic control, as it appears in computational finance in the case of dynamic optimal asset allocation.From the mathematical perspective, we propose a deep learning based numerical scheme for strongly coupled FBSDEs, stemming from stochastic control. In our application-oriented optimal portfolio asset allocation research, we take the perspective of a trader,who is allowed to trade in a risk-free bond, in stocks, and also in options, at a set of trading dates. A general framework results, where we can invest in multiple assets,and deal with quite

general objective functions.

报告人简介：Prof.dr.ir Comelis ("Kees") Oosterlee holds the chair of Financial Mathematics, in the Mathematical Institute of Utrecht University.He is currently Head of the Mathematical Institute.He has been working on computational problems in fnancial mathematics since 2000,.He is co-author of two textbooks("Multigrid" 2001, and "Mathematical Modeling and Computation in Finance",2019),and many scientific publications, The latter book has recently been translated and published in Chinese language.

欢迎大家参加!