主讲人Speaker: 常晋源    教授     西南财经大学

时间Date & Time: 2025年9月5日（周五），14:30--16:00

地点Venue:粤海校区汇星楼565会议室

内容简介/ Abstract:

We introduce an ordinary differential equation (ODE) based deep generative method for learning conditional distributions, named Conditional F\"ollmer Flow. Starting from a standard Gaussian distribution, the proposed flow could approximate the target conditional distribution very well when the time is close to 1. For effective implementation, we discretize the flow with Euler’s method where we estimate the velocity field nonparametrically using a deep neural network. Furthermore, we also establish the convergence result for the Wasserstein-2 distance between the distribution of the learned samples and the target conditional distribution, providing the first comprehensive end-to-end error analysis for conditional distribution learning via ODE flow. Our numerical experiments showcase its effectiveness across a range of scenarios, from standard nonparametric conditional density estimation problems to more intricate challenges involving image data, illustrating its superiority over various existing methods.

主讲人介绍/Biography of the speaker：

常晋源，西南财经大学光华特聘教授，国家杰出青年科学基金获得者、四川省特聘专家、四川省统计专家咨询委员会委员。主要从事大规模复杂数据分析相关的研究，先后担任统计学和计量经济学国际顶级学术期刊Journal of the Royal Statistical Society Series B、Journal of Business & Economic Statistics、Journal of the American Statistical Association的副主编，获得过国务院政府特殊津贴、霍英东教育基金会高等院校青年科学奖一等奖、教育部高等学校科学研究优秀成果奖、四川省青年科技奖等多项奖励。