Error analysis for the deep Kolmogorov method
This work offers theoretical error bounds for a popular deep learning method in PDE approximation, which is incremental as it builds on existing techniques.
The authors tackled the problem of analyzing the error of the deep Kolmogorov method for approximating solutions to heat PDEs, providing convergence rates for the mean square distance between the exact solution and the neural network approximation in terms of architecture size, sample points, and optimization error.
The deep Kolmogorov method is a simple and popular deep learning based method for approximating solutions of partial differential equations (PDEs) of the Kolmogorov type. In this work we provide an error analysis for the deep Kolmogorov method for heat PDEs. Specifically, we reveal convergence with convergence rates for the overall mean square distance between the exact solution of the heat PDE and the realization function of the approximating deep neural network (DNN) associated with a stochastic optimization algorithm in terms of the size of the architecture (the depth/number of hidden layers and the width of the hidden layers) of the approximating DNN, in terms of the number of random sample points used in the loss function (the number of input-output data pairs used in the loss function), and in terms of the size of the optimization error made by the employed stochastic optimization method.