数学学科Seminar第2435讲 PINN的失败及其隐式偏差

创建时间:  2023/08/01  龚惠英   浏览次数:   返回

报告题目 (Title):Failure of PINN and its implicit bias(PINN的失败及其隐式偏差)

报告人 (Speaker):罗涛 副教授 (上海交通大学数学科学学院)

报告时间 (Time):2023年8月4日(周五)10:00 -11:30

报告地点 (Place):校本部 E408

邀请人(Inviter):秦晓雪

主办部门:理学院数学系

报告摘要:Deep Neural Networks (DNNs) based numerical solvers, such as DeepRitz or PINN, are popular recently due to the quick development of the deep learning techniques. However, the performance of these methods is usually not quite good (especially for problems in low dimension). In this talk, we will discuss the performance of PINN methods for problems with discontinuities. First, for linear elliptic PDEs with discontinuous coefficients, we present by experiments that PINN cannot approximate the true solution. We then prove this by the method of introducing a modified equation. In the next step, we point out there is still some pattern behind this failure, which is a type of implicit bias. Finally, we will mention some extensions of these results to quasilinear elliptic equations and systems.

上一条:上海大学核心数学研究所——几何与分析综合报告第40讲 紧半单李群中的测度增长与Kemperman逆问题

下一条:数学学科Seminar第2434讲 一类(泛函)发展方程的判定与约简


数学学科Seminar第2435讲 PINN的失败及其隐式偏差

创建时间:  2023/08/01  龚惠英   浏览次数:   返回

报告题目 (Title):Failure of PINN and its implicit bias(PINN的失败及其隐式偏差)

报告人 (Speaker):罗涛 副教授 (上海交通大学数学科学学院)

报告时间 (Time):2023年8月4日(周五)10:00 -11:30

报告地点 (Place):校本部 E408

邀请人(Inviter):秦晓雪

主办部门:理学院数学系

报告摘要:Deep Neural Networks (DNNs) based numerical solvers, such as DeepRitz or PINN, are popular recently due to the quick development of the deep learning techniques. However, the performance of these methods is usually not quite good (especially for problems in low dimension). In this talk, we will discuss the performance of PINN methods for problems with discontinuities. First, for linear elliptic PDEs with discontinuous coefficients, we present by experiments that PINN cannot approximate the true solution. We then prove this by the method of introducing a modified equation. In the next step, we point out there is still some pattern behind this failure, which is a type of implicit bias. Finally, we will mention some extensions of these results to quasilinear elliptic equations and systems.

上一条:上海大学核心数学研究所——几何与分析综合报告第40讲 紧半单李群中的测度增长与Kemperman逆问题

下一条:数学学科Seminar第2434讲 一类(泛函)发展方程的判定与约简