The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
cs.LG, math.DS, stat.ML
Submitted: 2026-05-29
Updated: 2026-11-10
Code: https://github.com/DurstewitzLab/DynaMix-python
Terminology
Sources
- Position: A Dynamical Systems Perspective is Needed to Advance Time Series Modeling
- Teacher Forcing as Generalized Bayes: Optimization Geometry Mismatch in Switching Surrogates for Chaotic Dynamics
- Double projection for reconstructing dynamical systems: between stochastic and deterministic regimes
- Auto-differentiable data assimilation: Co-learning of states, dynamics, and filtering algorithms
- Probabilistic Retrofitting of Learned Simulators
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Gaussian Error Linear Units (GELUs)
- Adam: A Method for Stochastic Optimization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis