Mamba-Assisted Non-Markovian Closure for Reduced-Order Modeling
cs.LG, cs.NA, math.NA, stat.ML
Submitted: 2026-06-03
Updated: 2026-08-31
Comments: Code will be released upon acceptance
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Gradient-free online learning of subgrid-scale dynamics with neural emulators
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Efficiently Modeling Long Sequences with Structured State Spaces
- Stabilizing PDE--ML coupled systems
- Differentiable Physics-Neural Models enable Learning of Non-Markovian Closures for Accelerated Coarse-Grained Physics Simulations
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks