no code implementations • 9 Sep 2021 • Yiqi Gu, John Harlim, Senwei Liang, Haizhao Yang
In this paper, we consider the density estimation problem associated with the stationary measure of ergodic It\^o diffusions from a discrete-time series that approximate the solutions of the stochastic differential equations.
1 code implementation • 12 Jun 2021 • Senwei Liang, Shixiao W. Jiang, John Harlim, Haizhao Yang
In a well-posed elliptic PDE setting, when the hypothesis space consists of neural networks with either infinite width or depth, we show that the global minimizer of the empirical loss function is a consistent solution in the limit of large training data.
no code implementations • 21 May 2021 • He Zhang, John Harlim, Xiantao Li
We find that sufficient conditions for such a linear dependence result are through learning algorithms that produce a uniformly Lipschitz and consistent estimator in the hypothesis space that retains certain characteristics of the drift coefficients, such as the usual linear growth condition that guarantees the existence of solutions of the underlying SDEs.
no code implementations • 13 Oct 2019 • John Harlim, Shixiao W. Jiang, Senwei Liang, Haizhao Yang
This article presents a general framework for recovering missing dynamical systems using available data and machine learning techniques.