arXiv:2611.25274v1 Announce Type: new
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.
Trending
- Intelligent Embedding Pruning for Large-Scale Recommendation Models
- Evaluating AI Scientists in Agentic Twins of Real Labs
- UN court cites military Facebook posts while finding Myanmar guilty of genocide
- DS3M: Deep structured state space models for nonlinear system identification on modern hardware
- Apple joins the race for AI agents that control your device while raising new barriers for competitors
- Watch Where You Linearize: Predicting and Correcting Model-Merging Interference
- How FAA can modernize US national airspace system without emergency ground stops
- The fallout from Nvidia’s Jensen Huang scandal continues
