Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction
cs.LG, stat.ML
Submitted: 2026-09-15
Updated: 2026-09-15
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Message Passing Neural PDE Solvers
- Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
- The Bayesian Approach To Inverse Problems
- Deep Kalman Filters
- Neural Operator: Graph Kernel Network for Partial Differential Equations
- Transformer for Partial Differential Equations' Operator Learning
- Learning Mesh-Based Simulation with Graph Networks
- Variational Autoencoding Neural Operators
- Learned Coarse Models for Efficient Turbulence Simulation
- Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit
- Improved Operator Learning by Orthogonal Attention
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