system-identification

This paper proposes Fractional-Order Ordinary-Least-Squares Grid-Search (FO-GS), a method for identifying fractional-order linear time-invariant systems from a single trajectory, with theoretical error bounds and experimental validation.

This paper proposes a regularized least squares training approach for quadratic neural networks, providing closed-form expressions for weights and sensitivity, with applications to system identification.

This paper studies adaptive symmetry discovery for dynamical system identification, showing that known symmetries reduce the trajectory length needed for identification and proposing a method to learn unknown symmetry groups from a single trajectory to achieve the same optimal length.

This paper proposes a provable two-stage pipeline that distills nonlinear dynamical systems into compact linear state-space models using convex optimization, with theoretical guarantees and experiments on LDS benchmarks and MuJoCo.

Proposes a hierarchical Bayesian framework for meta-learning in dynamical systems from multiple sparse, noisy datasets, using gradient-based MCMC with an embedded ODE solver for efficient posterior inference of shared and dataset-specific parameters.

This paper introduces In-Context World Modeling (ICWM), a framework that enables robot policies to infer system variables from self-generated interactions, allowing adaptation to novel configurations without parameter updates by treating system identification as an in-context adaptation problem. It outperforms standard VLA baselines on novel camera viewpoints in simulation and real-world experiments.

The paper proposes a class of time-varying deep state-space models where dynamics are learned via a basis function expansion, enabling adaptive modeling of switching systems. The approach outperforms time-invariant counterparts on synthetic switching data and a speech denoising task.

This paper extends Port-Hamiltonian Neural Networks (PHNNs) to partial differential equations (PDEs) for learning nonlinear string dynamics from data. The approach recovers both the Hamiltonian and dissipation, outperforming non-physics-informed baselines in accuracy and interpretability.