8 citations · 18 across the 4 of their papers we have counts for
4 papers
Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
Xin Liu, Wei Tao, Wei Li +3
Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural net…
BI-GreenNet: Learning Green's functions by boundary integral network
Guochang Lin, Fukai Chen, Pipi Hu +4
Green's function plays a significant role in both theoretical analysis and numerical computing of partial differential equations (PDEs). However, in most cases, Green's function is…
M2N: Mesh Movement Networks for PDE Solvers
Wenbin Song, Mingrui Zhang, Joseph G. Wallwork +8
Mainstream numerical Partial Differential Equation (PDE) solvers require discretizing the physical domain using a mesh. Mesh movement methods aim to improve the accuracy of the num…
BINet: Learning to Solve Partial Differential Equations with Boundary Integral Networks
Guochang Lin, Pipi Hu, Fukai Chen +4
We propose a method combining boundary integral equations and neural networks (BINet) to solve partial differential equations (PDEs) in both bounded and unbounded domains. Unlike e…