cs.LGNov 18, 2026

DS3M: Deep structured state space models for nonlinear system identification on modern hardware

Authors: Marco Roschkowski, Hannes Gernandt

Organizations: University of Wuppertal, Wuppertal, Germany

Abstract

Neural state-space identification learns dynamical models from measured inputs and outputs. SUBNET combines this task with an encoder that estimates initial states from short measurement histories. Its continuous-time version requires many successive neural-network evaluations during numerical integration, resulting in slow training speed which is a major limitation for practical use cases. We propose deep structured state space models (DS3M), which combine compact nonlinear dynamical components in parallel and in series. Custom GPU kernels implemented with Triton reduce the launch and memory overhead of their sequential evaluation. We explain this construction, describe a port-Hamiltonian variant, and present various benchmark comparisons of accuracy and training time.

Figures & tables

Explore similar work

CardsList
  1. Online learning of neural state-space models

    Jul 20, 2026Bendegúz Györök, Tamás Péni, Maarten Schoukens +1Online System IdentificationNonlinear System Identification

  2. Latent Matters: Learning Deep State-Space Models

    Feb 26, 2026Alexej Klushyn, Richard Kurle, Maximilian Soelch +2State Space ModelsLatent Dynamics Modeling

  3. Efficient Learning of Deep State Space Models via Importance Smoothing

    May 20, 2026John-Joseph Brady, Nikolas Nusken, Yunpeng LiVariational InferenceState Space Models