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

ds3m:-deep-structured-state-space-models-for-nonlinear-system-identification-on-modern-hardware

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

[Submitted on 18 Nov 2026]

View PDF HTML (experimental)

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.

Submission history

From: Marco Roschkowski [view email]
[v1] Wed, 18 Nov 2026 23:06:23 UTC (421 KB)