2026年随机计算及相关领域前沿进展暑期学校系列学术报告 | Deep learning numerical methods for high-dimensional nonlinear PIDEs and FBSDEJs based on the probabilistic representation of solutions
报 告 人: 王晚生
所在单位: 上海师范大学
报告地点: 吉林大学正新楼106
报告时间: 2026-07-31 16:00:00
报告简介:

We propose deep learning algorithms for solving high-dimensional parabolic integro-differential equations (PIDEs) and high-dimensional forward-backward stochastic differential equations with jumps (FBSDEJs), where the jump-diffusion process is derived by a Brownian motion and an independent compensated Poisson random measure. In the novel algorithm for coupled FBSDEJs, a pair of deep neural networks for the approximations of the gradient and the integral kernel is introduced in a crucial way based on the deep FBSDE method. For FBSDEJs with small-to-moderate jump sizes and moderate jump intensities we propose the novel FBSJNN framework in which a single neural network to approximate the PIDE solution is used, while leveraging Taylor expansion to eliminate the need for a separate approximation of the non-local integral term. For both the deep learning algorithms, we derive the error estimates by exploring the error bound of Euler time discretization and the simulation error of deep learning algorithm. For the former, it is also shown that the approximation error converges to zero given the universal approximation capability of neural networks. several numerical examples are provided to show the efficiency of these proposed algorithms.

上一篇 下一篇
主讲人简介:
王晚生,上海师范大学教授,博导,教务处副处长,数学科学研究所所长。2008年6月博士毕业于湘潭大学,华中科技大学、剑桥大学博士后,先后在长沙理工大学、上海师范大学工作。主要从事微分方程数值解法及应用方面的教学研究工作,在金融期权模型理论分析和快速算法、微分方程保稳定性算法和自适应算法、数据同化和深度学习算法等方面取得了一些成绩,以第一作者在《Numer. Math.》、《SIAM J. Numer. Anal.》、《Math. Comput.》、《SIAM J. Sci. Comput.》、《Inver. Problem》等期刊上发表学术论文100余篇,以第一完成人获上海市和湖南省自然科学奖二等奖各1项、霍英东青年教师奖等。主持国家自然科学基金项目4项、湖南省杰青等科研项目。曾访问北京大学、加州大学尔湾分校、剑桥大学等国内外名校。曾入选湖南省新世纪“121人才工程”、湖南省普通高校学科带头人等人才计划,系AAMM编委、中国仿真学会理事、中国工业与应用数学学会金融科技与算法专委会常务委员、中国数学会计算数学分会理事等。