| --- |
| license: cc-by-4.0 |
| pipeline_tag: time-series-forecasting |
| datasets: |
| - williamgilpin/dysts |
| --- |
| |
| # DynaMix |
|
|
| [](https://arxiv.org/abs/2505.13192) (accepted NeurIPS 2025 paper) |
|
|
| DynaMix is a foundation model for zero-shot inference of dynamical systems that preserves long-term statistics. Unlike traditional approaches that require retraining for each new system, DynaMix provides context driven generalization to unseen dynamical systems. |
|
|
| - **Accurate Zero-Shot Dynamical Systems Reconstruction**: DynaMix generalizes across diverse dynamical systems without fine-tuning, accurately capturing attractor geometry and long-term statistics. |
| - **Context Felxible Dynamics Modeling**: The multivariate architecture captures dependencies across system dimensions and adapts to different dimensionalities and context lengths. |
| - **Efficient and Lightweight**: Designed to be efficient with a few thousand parameters, DynaMix can also run on CPU for inference, and is enabling orders-of-magnitude faster inference than traditional foundation models. |
| - **General Time Series Forecasting**: Extends beyond DSR to general time series forecasting using adaptable embedding techniques. |
|
|
| For complete documentation and code, visit the [DynaMix repository](https://github.com/DurstewitzLab/DynaMix-python). |
|
|
| ## Model Description |
|
|
| DynaMix is based on a mixture of experts (MoE) architecture operating in latent space: |
|
|
| 1. **Expert Networks**: Each expert is a specialized dynamical model, given trhough RNN based architectures |
|
|
| 2. **Gating Network**: Selects experts based on the provided context and current latent representation of the dynamics |
|
|
| By aggregating the expert weighting with the expert prediction the next state is predicted. |
|
|
| ## Usage |
|
|
| To load the model in python using the corresponding codebase [DynaMix repository](https://github.com/DurstewitzLab/DynaMix-python), use: |
|
|
| ```python |
| from src.utilities.utilities import load_hf_model |
| |
| # Initialize model with architecture |
| model = load_hf_model(model_name="dynamix-3d-alrnn-v1.0") |
| ``` |
|
|
| Given context data from the target system with shape (`T_C`, `S`, `N`) (where `T_C` is the context length, `S` the number of sequences that should get processed and `N` the data dimensionality), generate forecasts by passing the data through the `DynaMixForecaster` along with the loaded model. Further details can be found in the GitHub repository [DynaMix repository](https://github.com/DurstewitzLab/DynaMix-python). |
|
|
|
|
| ## Citation |
|
|
| If you use DynaMix in your research, please cite our paper: |
|
|
| ``` |
| @misc{hemmer2025truezeroshotinferencedynamical, |
| title={True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics}, |
| author={Christoph Jürgen Hemmer and Daniel Durstewitz}, |
| year={2025}, |
| eprint={2505.13192}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.LG}, |
| url={https://arxiv.org/abs/2505.13192}, |
| } |
| ``` |
