AI & ML
DS3M: Deep structured state space models for nonlinear system identification on modern hardware
arXiv cs.SY0 views
arXiv:2611.25274v1 Announce Type: cross 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.
Source:https://arxiv.org/abs/2611.25274PreviousSmall-Gain Analysis of Robust Event-Triggered Extremum Seeking for Scalar MapsNextThe Ces\`aro Value Iteration
Related posts

Tối ưu hóa kiến trúc LLM với Perplexity Orchestrator API: Multi-Cloud Failover và Drop-in Integration
0dev.to
From Checks to Decisions
0dev.to
Test your Android app with Claude Code on a cloud phone
0dev.to
If you can't explain something in simple terms, you don't understand it (2017)
0Hacker News
The AI free tier is shrinking: five tools that changed pricing in 2026
0dev.to

Hyphen vs En Dash vs Em Dash: Differences, Examples, and When to Use Each
0dev.to