报告学者：张希承教授

报告者单位：北京理工大学

报告时间：2024年5月29日（周三）16:00-17:00

报告地点：学活会议室1005室

报告摘要：Drawing from the theory of stochastic differential equations, we introduce  a new sampling method for {\it known} distributions, as well as a new algorithm for diffusion generative models with {\it unknown} distributions. Our approach is inspired by the concept of the reverse diffusion process, which has been widespread adoption in diffusion generative models. Furthermore, we compute the explicit convergence rate based on the smooth ODE flow. Numerical experiments exhibit the effectiveness of our method. In particular, unlike the traditional Langevin method, our sampling method does not require any regularity assumptions about the density function of the target distribution. We also apply it to the optimization problem.

报告人简介： 张希承，北京理工大学数学与统计学院教授。研究方向主要为随机分析及其应用。2013年获国家自然科学基金杰出青年项目资助，2016年获教育部“长江学者”特聘教授。