Approximating Stochastic Evolution Equations with Additive White and Rough Noises
For researchers in numerical analysis of stochastic PDEs, this provides refined error bounds for Galerkin methods, though the improvement is incremental.
The paper analyzes Galerkin approximations for stochastic evolution equations driven by additive Gaussian noise, achieving optimal error estimates that remove an infinitesimal factor present in prior work.
In this paper, we analyze Galerkin approximations for stochastic evolution equations driven by an additive Gaussian noise which is temporally white and spatially fractional with Hurst index less than or equal to $1/2$. First we regularize the noise by the Wong-Zakai approximation and obtain its optimal order of convergence. Then we apply the Galerkin method to discretize the stochastic evolution equations with regularized noises. Optimal error estimates are obtained for the Galerkin approximations. In particular, our error estimates remove an infinitesimal factor which appears in the error estimates of various numerical methods for stochastic evolution equations in existing literatures.