Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Numerically Solving Parametric Families of High-Dimensional Kolmogorov Partial Differential Equations via Deep Learning
Julius Berner, Markus Dablander, Philipp Grohs
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 |
|---|---|---|---|
| Train the Multilevel network for 24k gradient steps instead of using its initial prediction | Parametric Black-Scholes solver · Black-Scholes model | average relative L1 error: 0.6812 ± 0.0704 -> 0.0011 ± 0.0001 | Improved |
| Train the Multilevel network for 28k gradient steps instead of using its initial prediction | Parametric Basket option solver · Basket option | average relative L1 error: 0.7912 ± 0.0276 -> 0.0039 ± 0.0001 | Improved |
| Train the Multilevel network for 28k gradient steps instead of using its initial prediction | Parametric heat-equation solver · Heat equation, paraboloid initial condition | average relative L1 error: 0.9609 ± 0.0052 -> 0.0056 ± 0.0000 | Improved |
| Train the Multilevel network for 28k gradient steps instead of using its initial prediction | Parametric heat-equation solver · Heat equation, Gaussian initial condition | average relative L1 error: 0.2035 ± 0.0714 -> 0.0019 ± 0.0002 | Improved |
Closest papers by meaning
- SHoP: A Deep Learning Framework for Solving High-Order Partial Differential Equations (AAAI 2024 · similarity 0.86)
- Deep Learning Alternatives Of The Kolmogorov Superposition Theorem (ICLR 2025 · similarity 0.85)
- Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods (ICLR 2025 · similarity 0.84)
- Toward Efficient Kernel-Based Solvers for Nonlinear PDEs (ICML 2025 · similarity 0.84)
- An Interpretable Approach to the Solutions of High-Dimensional Partial Differential Equations (AAAI 2024 · similarity 0.84)
- MC^2: Monte Carlo Correction for Fast Elliptic PDE Solving (NeurIPS 2026 · similarity 0.84)
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.
