Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Scalable Bayesian Inference for Nonlinear Conservation Laws
Tim Weiland, Philipp Hennig
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 |
|---|---|---|---|
| replace PINN with GP-FVM for source identification | GP-FVM · Source identification (advection-diffusion) | source RMSE: 0.76 -> 0.44 | Improved |
| replace PINN with GP-FVM for source identification | GP-FVM · Source identification (advection-diffusion) | runtime: approximately 5 minutes -> 2 seconds (150x) | Improved |
| use conservative FVM discretization instead of GP collocation | GP-FVM (minimal) · 2D Burgers | L2 error: within 2--3x of classical vs ~10x worse | Improved |
| use full state (add flux quantities) instead of minimal state (ablation) | GP-FVM · 2D Burgers | L2 error | No clear effect |
| use full state instead of minimal state (ablation) | GP-FVM · 2D Burgers | runtime: state dimension 8N^2 -> 26N^2 | Hurt |
| use sparse approximation with rho=5 and smoother kernels (ablation) | GP-FVM sparse · 1D Poisson (N up to 160) | L2 error: 16% fill at N=160 | Hurt |
| add three extra observations of concentration (ablation) | GP-FVM · Source identification | source samples | Improved |
Closest papers by meaning
- Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems (NeurIPS 2025 · similarity 0.87)
- Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models (NeurIPS 2024 · similarity 0.86)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.86)
- Closing the Approximation Gap in Simulation-free Latent SDEs (NeurIPS 2026 · similarity 0.85)
- Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation (ICML 2025 · similarity 0.85)
- Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws (ICML 2024 · similarity 0.85)
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.
