东南大学数学学院将于2026.10.20举办Neural ODEs学术报告

东南大学数学学院邀请专家申请表

报告人 李兹谦 单位 德国埃尔朗根-纽伦堡大学

报告题目 Neural ODEs: Approximation Theory and Operator Learning

报告时间 2026 年 10 月 20 日周二

下午 16:00-17:00 地点 腾讯会议：501-426-796

邀请人 李梦妮

报告摘要

Neural Ordinary Differential Equations (NODEs) have emerged as a

powerful paradigm for modeling continuous-time systems. This talk

explores the theoretical foundations and practical applications of NODEs

in scientific machine learning through two recent works. First, we

introduce semi-autonomous NODEs (SA-NODEs) for approximating

dynamical systems, establishing their universal approximation properties

and quantitative convergence rates with significantly reduced model

complexity. Second, we present NODE-ONet, a novel operator learning

framework for solving PDEs. By integrating physics-encoded NODEs

into an encoder-decoder architecture, NODE-ONet effectively decouples

spatial and temporal variables, enabling highly efficient numerical

predictions and robust extrapolation beyond training time frames.

报告人

简介

李兹谦，德国埃尔朗根-纽伦堡大学博士研究生（导师:Enrique Zuazua

教授），2026 年 6 月获吉林大学博士学位（导师:汤涛教授、张然教

授）。研究方向包括深度学习求解微分方程、流体混合的最优控制

理论与数值计算。相关成果发表在 SINUM、M3AS、JSC 等期刊。