Deep backward multistep high-order regression methods for high dimensional nonlinear parabolic partial differential equations
Abstract
We propose a deep backward multistep high-order regression (MHDBR) method for semilinear parabolic partial differential equations through their backward stochastic differential equation representations. The method combines multistep time discretization with regression targets formed by conditional expectations. Under explicit regularity, starting-value, forward-approximation and network-moment assumptions, we prove an error bound separating time discretization, conditional Monte Carlo sampling and neural-network approximation. The analysis assumes exact population minimization; finite-training-sample generalization and optimization errors are not included. For generators independent of the gradient variable, suitably constrained GroupSort networks and sufficiently large conditional sample sizes give order J in the stated nodal L2 error norm. The required network sizes depend on dimension, so this result does not establish dimension-independent complexity. We present a reproducible time-discretization test satisfying the analytical assumptions and three broader neural-network benchmarks, whose relation to the assumptions is discussed explicitly.
Related
- A semi-generating function approach to the stability of implicit-explicit multistep methods for nonlinear parabolic equations
- Stability and Error Analysis of Multistep IMEX Local Discontinuous Galerkin Methods for One-Dimensional Nonlinear Fourth-Order Evolution Problems
- Parabolic Poincaré inequalities and maximal function estimates for systems of partial differential equations
- Existence of weak solutions to two-phase Stefan problems for parabolic partial differential equation system
- Harnack-type inequalities for nonlocal doubly nonlinear parabolic equations
BibTeX
@misc{han2026deep,
title = {{Deep backward multistep high-order regression methods for high dimensional nonlinear parabolic partial differential equations}},
author = {Qiang Han and Shaolin Ji and Zihao Xv},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.10570},
eprint = {2611.10570},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.10570},
}
RIS
TY - UNPB
TI - Deep backward multistep high-order regression methods for high dimensional nonlinear parabolic partial differential equations
AU - Qiang Han
AU - Shaolin Ji
AU - Zihao Xv
PY - 2026
DA - 2026/11/07
PB - arXiv
DO - 10.48550/arxiv.2611.10570
UR - https://arxiv.org/abs/2611.10570
AB - We propose a deep backward multistep high-order regression (MHDBR) method for semilinear parabolic partial differential equations through their backward stochastic differential equation representations. The method combines multistep time discretization with regression targets formed by conditional expectations. Under explicit regularity, starting-value, forward-approximation and network-moment assumptions, we prove an error bound separating time discretization, conditional Monte Carlo sampling and neural-network approximation. The analysis assumes exact population minimization; finite-training-sample generalization and optimization errors are not included. For generators independent of the gradient variable, suitably constrained GroupSort networks and sufficiently large conditional sample sizes give order J in the stated nodal L^2 error norm. The required network sizes depend on dimension, so this result does not establish dimension-independent complexity. We present a reproducible time-discretization test satisfying the analytical assumptions and three broader neural-network benchmarks, whose relation to the assumptions is discussed explicitly.
ER -