A Class of Stochastic Runge-Kutta Methods for Stochastic Differential Equations Converging with Order 1 in $L^p$-Norm

TL;DR

This paper introduces a new class of efficient stochastic Runge-Kutta methods for solving Itô and Stratonovich SDEs, achieving strong order 1 convergence with minimal computational cost and broad applicability.

Contribution

The paper develops a novel class of SRK methods requiring only two stages for order 1 convergence, applicable to both commutative and non-commutative noise, with explicit coefficient conditions and efficiency improvements.

Findings

Methods achieve strong order 1 convergence in $L^p$-norm.

Computational cost scales linearly with SDE and Wiener process dimensions.

Numerical experiments confirm theoretical convergence results.

Abstract

For the approximation of solutions for It\^o and Stratonovich stochastic differential equations (SDEs)a new class of efficient stochastic Runge-Kutta (SRK) methods is developed. As the main novelty only two stages are necessary for the proposed SRK methods of order 1 that can be applied to SDEs with non-commutative or with commutative noise. In addition, a variant of the SRK method for SDEs with additive noise is presented. All proposed SRK methods cover also the case of drift-implicit schemes and general order conditions for the coefficients are calculated explicitly. The new class of SRK methods is highly efficient in the sense that it features computational cost depending only linearly on the dimension of the SDE and on the dimension of the driving Wiener process. For all proposed SRK methods strong convergence with order 1 in $L^p$-norm for any $p \geq 2$ is proved. Moreover, sufficient conditions for approximated iterated stochastic integrals are established such that convergence with order 1 in $L^p$-norm is preserved if they are applied for the SRK method. The presented theoretical results are confirmed by numerical experiments.