This paper provides a new identifiability theorem for causal representation learning to uncover physical system parameters from raw data without predefined libraries.
March 17, 2026
Original Paper
Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention
arXiv · 2603.14483
The Takeaway
It moves beyond the limitation of 'candidate libraries' in system identification, allowing practitioners to discover the underlying structure of dynamical systems directly from trajectories. It uses a sparsity-regularized transformer to reveal state-dependent causal structures with theoretical guarantees.
From the abstract
Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of candidate functions chosen via available domain knowledge. In contrast, deep learning can demonstrably model systems of broad complexity with high fidelity, but black-box function approximation typically fails to yield explicit descriptive or disentangled represe