stat.MLNov 7, 2026

Deep backward multistep high-order regression methods for high dimensional nonlinear parabolic partial differential equations

Authors: Qiang Han, Shaolin Ji, Zihao Xv

Organizations: School of Mathematics, Yangzhou University, Yangzhou 225002, China. · Zhongtai Securities Institute for Financial Studies, Shandong University, Jinan, Shandong 250100, China.

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 JJ in the stated nodal L2L^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.

Figures & tables

Explore similar work

CardsList
  1. A Zeroth-Order Deep Learning Method for Fully Nonlinear Parabolic Partial Differential Equations with Unknown Coefficients

    Jun 23, 2026Yanwei Jia, Du Ouyang, Huyên Pham +1Neural PDE SolversPDE Solving

  2. Walk-on-Spheres Monte Carlo and deep neural network approximations of elliptic PDEs with drift and killing

    Aug 10, 2026Konrad Kleinberg, Thomas KruseNeural PDE SolversPDE Solving

  3. Unbiased and Second-Order-Free Training for High-Dimensional PDEs

    May 14, 2026Jaemin Seo, Surin Lee, Jae Yong LeeStochastic Differential EquationsNeural PDE Solvers