Integration Matters for Learning PDEs with Backward SDEs

NeurIPSSpotlight2025

Authors
Sungje Park, Stephen Tu
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Backward stochastic differential equation (BSDE)-based deep learning methods provide an alternative to Physics-Informed Neural Networks (PINNs) for solving high-dimensional partial differential equati…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

physics

← All NeurIPS 2025 Spotlight papers · Browse the whole archive