Learning-enabled Parameter Synthesis for Nonlinear Systems from Signal Temporal Logic
arXiv:2607.08899
2026
Dynamics
2 ideas extracted · analyzed Aug 30, 2026
What the math gives to ML
The paper combines gradient-based parameter optimization with set-based forward reachability to synthesize nonlinear-system parameters that satisfy continuous-time Signal Temporal Logic specifications for uncertain initial conditions. Its transferable asset is a sound robustness certificate: optimizing nominal or sampled trajectories is followed by computing a lower bound on STL robustness over an entire reachable tube. This mechanism can be transferred to neural ODEs, recurrent state-space models, and neural controllers by treating hidden-state initialization and bounded inputs as uncertainty sets. A second transfer uses the certified robustness margin to gate optimizer steps, creating a verification-aware trust region around safe network parameters.
Ideas from this paper
✗ Failed on benchmark
2026
Train a neural ODE or continuous-time recurrent model directly against STL robustness, while requiring the resulting trajectory tube to satisfy the specification for every initial hidden state in a bounded set. Differentiable robustness provides an optimization objective, and interval, zonotope, or other set-based reachability provides a post-update certificate that prevents success caused by a narrow nominal trajectory.
Useful8/10
Difficulty6/10
Novelty8/10
✗ Failed on benchmark
2026
Use the reachability verifier as an optimization controller: permit a neural controller update only when the proposed parameter step remains inside a certified STL-safe trust region, and shrink the region when the reachable robustness margin collapses. This turns verification from an expensive final check into feedback that prevents gradient descent from crossing a temporal-logic feasibility boundary.
Useful7/10
Difficulty7/10
Novelty8/10