BIMSA >
控制理论和非线性滤波讨论班
Rectified Deep Neural Networks Overcome the Curse of Dimensionality When Approximating Solutions of McKean-Vlasov Stochastic Differential Equations
Rectified Deep Neural Networks Overcome the Curse of Dimensionality When Approximating Solutions of McKean-Vlasov Stochastic Differential Equations
组织者
演讲者
孙泽钜
时间
2023年12月21日 14:30 至 15:00
地点
理科楼A-230
摘要
In this talk, I will review the paper entitled ‘Rectified Deep Neural Networks Overcome the Curse of Dimensionality When Approximating Solutions of McKean-Vlasov Stochastic Differential Equations’, in which the authors prove that rectified deep neural networks do not suffer from the curse of dimensionality when approximating McKean–Vlasov SDEs in the sense that the number of parameters in the deep neural networks only grows polynomially in the space dimension d of the SDE and the reciprocal of the accuracy .