Research map / Probabilistic and scientific modeling / Differential equations and PDEs
From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs
Lorenz Richter, Leon Sallandt, Nikolas Nüsken
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use tensor trains instead of neural networks for function approximation | BSDE solver for 100-dimensional HJB · HJB equation (d=100) | relative error, RMSE, PDE loss | Improved |
| use BSDE losses instead of the other regression losses (ablation) | tensor train and neural network solvers · HJB equation (d=100) | relative error, RMSE, PDE loss | Improved |
| use implicit instead of explicit BSDE loss (ablation) | BSDE solver · HJB equation (d=100) | relative error | No clear effect |
| increase polynomial degree of tensor train ansatz functions (ablation) | tensor train with implicit BSDE loss · HJB equation, varying dimension | relative error | Mixed |
Closest papers by meaning
- Solving high-dimensional parabolic PDEs using the tensor train format (ICML 2021 · similarity 0.97)
- UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs (ICML 2024 · similarity 0.88)
- Integration Matters for Learning PDEs with Backwards SDEs (NeurIPS 2025 · similarity 0.88)
- S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks (NeurIPS 2026 · similarity 0.88)
- Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers (NeurIPS 2025 · similarity 0.88)
- CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
