arXiv:2102.10621 Abstract | arXiv Analytics

arXiv:2102.10621 [math.AP]Abstract References Reviews Resources

Convergence rate of DeepONets for learning operators arising from advection-diffusion equations

Beichuan Deng, Yeonjong Shin, Lu Lu, Zhongqiang Zhang, George Em Karniadakis

Published 2021-02-21Version 1

We present convergence rates of operator learning in [Chen and Chen 1995] and [Lu et al. 2020] when the operators are solution operators of differential equations. In particular, we consider solution operators of both linear and nonlinear advection-diffusion equations.

Categories: math.AP, cs.NA, math.NA

Keywords: convergence rate, learning operators arising, solution operators, nonlinear advection-diffusion equations, differential equations

Related articles: Most relevant | Search more

arXiv:1907.06030 [math.AP] (Published 2019-07-13)

On the convergence rate of some nonlocal energies

Antonin Chambolle, Matteo Novaga, Valerio Pagliari

arXiv:2010.15410 [math.AP] (Published 2020-10-29)

Final size and convergence rate for an epidemic in heterogeneous population

Luís Almeida, Pierre-Alexandre Bliman, Grégoire Nadin, Benoît Perthame, Nicolas Vauchelet

arXiv:1206.2601 [math.AP] (Published 2012-06-12, updated 2013-07-05)

Error estimates and convergence rates for the stochastic homogenization of Hamilton-Jacobi equations

Scott N. Armstrong, Pierre Cardaliaguet, Panagiotis E. Souganidis