English 清华大学 旧版入口 人才招聘

论坛讲座

【系综合学术报告】&【荷思系友报告】第20期 Solving dynamic portfolio selection problems via score-based diffusion models

系综合学术报告】&【荷思系友报告】第20


报告题目Solving dynamic portfolio selection problems via score-based diffusion models

报告人Fengyi Yuan (The Chinese University of Hong Kong, Shenzhen)

时间20251226日上午10:00-12:00(星期五)

地点:清华大学双清综合楼304

摘要In this work, we tackle the dynamic mean-variance portfolio selection problem in a {\it model-free} manner, based on (generative) diffusion models. We propose using data sampled from the real model ℙ (which is unknown) with limited size to train a generative model ℚ (from which we can easily and adequately sample). With adaptive training and sampling methods that are tailor-made for time series data, we obtain quantification bounds between ℙ and ℚ in terms of the adapted Wasserstein metric  AW2. Importantly, the proposed adapted sampling method also facilitates {\it conditional sampling}. In the second part of this paper, we provide the stability of the mean-variance portfolio optimization problems in AW2. Then, combined with the error bounds and the stability result, we propose a policy gradient algorithm based on the generative environment, in which our innovative adapted sampling method provides approximate scenario generators. We illustrate the performance of our algorithm on both simulated and real data. For real data, the algorithm based on the generative environment produces portfolios that beat several important baselines, including the Markowitz portfolio, the equal weight (naive) portfolio, and S\&P 500.

Bio: Fengyi Yuan is an Assistant Professor at School of Science and Engineering (SSE) of the Chinese University of Hong Kong, Shenzhen. He obtained his B.Sc. (2019) and Ph.D. (2024) from Department of Mathematical Sciences, Tsinghua University. Before his current position, he was a Byrne Research Assistant Professor at the University of Michigan, Ann Arbor from 2024 to 2025, working in the group led by Prof. Erhan Bayraktar. His research spans Stochastic Control, Mathematical Finance, Mean-field Control and Game, Model Uncertainty in Dynamic Decision Problems. His work has been published in leading journals, including Mathematical Finance, Finance and Stochastics, SIAM Journal on Control and Optimization, Mathematics of Operations Research, SIAM Journal on Financial Mathematics and  Insurance: Mathematics and Economics.

邀请人:梁宗霞