fSRD: Fuzzy Spectral Region Decomposition -- Automated Multi Operator Koopman Representations via an Adaptive Spectral Learning Architecture
cs.LG, math.DS
Submitted: 2026-07-20
Updated: 2026-09-14
Comments: 66 pages, 30 figures, corresponding author = Charles Bokor. Updated version with minor corrections, clarifications, and improvements to notation and reproducibility. Typographical and presentation errors have also been corrected
License: http://creativecommons.org/licenses/by/4.0/
The gist: Highly nonlinear chaotic dynamical systems remain difficult to model due to fundamental trade-offs between complexity, expressivity, and data efficiency.
Terminology
Abstract
Highly nonlinear chaotic dynamical systems remain difficult to model due to fundamental trade-offs between complexity, expressivity, and data efficiency. Modern machine learning methods achieve strong predictive performance but often rely on a-priori system knowledge or curated data with limited interpretability. Koopman operator theory offers a promising direction via linear representation in an infinite-dimensional observable space. However, many data-driven Koopman methods seek globally valid operators for which useful finite-dimensional spectral embeddings remain difficult to identify under these constraints. To overcome associated limitations, we introduce Fuzzy Spectral Region Decomposition (fSRD), a fully automated learning framework for estimating finite Koopman representation via multiple operators. The proposed method realizes a data-adaptive framework for assembling locally invariant embeddings, termed Invariant Decomposition. fSRD achieves highly accurate linear reconstructions of nonlinear systems while learning finite-dimensional representations of their induced evolution operators, bridging interpretable operator-theoretic models with expressive data-driven sequence learning. These embeddings are adaptively constructed via a global fuzzy tree model, drawing inspiration from fuzzy neural architectures to learn the induced dynamics while prioritizing parsimonious solutions. Empirical results across canonical chaotic systems (e.g., Lorenz and Duffing) and high-dimensional real-world data demonstrate strong predictive accuracy, interpretability, and robust expressivity across data-rich and data-limited regimes, highlighting the method's generality.
Sources
- Modern Koopman Theory for Dynamical Systems
- The Multiverse of Dynamic Mode Decomposition Algorithms
- Iterated Function Systems: A Comprehensive Survey
- Explainable AI: current status and future directions
- Pushing the complexity barrier: diminishing returns in the sciences
- Optimal construction of Koopman eigenfunctions for prediction and control
- Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
- Spectrum of the Koopman Operator, Spectral Expansions in Functional Spaces, and State Space Geometry
- Data-Driven Operator Theoretic Methods for Global Phase Space Learning
- Data-Driven Operator Theoretic Methods for Phase Space Learning and Analysis
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