DBR reformulates backward losses via conditional expectations and Monte Carlo averaging to create smoother training targets for deep neural network solvers of high-dimensional nonlinear PDEs, yielding competitive benchmarks and half-order convergence under stated assumptions.
and Menozzi, S.(2008).An interpolated stochastic algorithm for quasi-linear PDEs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A deep backward regression-based scheme for high-dimensional nonlinear partial differential equations
DBR reformulates backward losses via conditional expectations and Monte Carlo averaging to create smoother training targets for deep neural network solvers of high-dimensional nonlinear PDEs, yielding competitive benchmarks and half-order convergence under stated assumptions.