APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
cs.LG
Submitted: 2024-10-31
Updated: 2024-10-31
Code: https://github.com/tum-pbs/apebench
Project page: https://tum-pbs.github.io/apebench
Terminology
Sources
- Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation
- GraphCast: Learning skillful medium-range global weather forecasting
- Differentiability in Unrolled Training of Neural Physics Simulators on Transient Dynamics
- CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics
- Learned Coarse Models for Efficient Turbulence Simulation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks