mlsanityData to 14 Oct 2026

VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change

arXiv 2505.14001 ↗First posted 20 May 2025cs.AI cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous systems operating in the real world encounter a range of uncertainties. Probabilistic neural Lyapunov certification is a powerful approach to proving safety of nonlinear stochastic dynamical systems. When faced with changes beyond the modeled uncertainties, e.g., unidentified obstacles, probabilistic certificates must be transferred to the new system dynamics. However, even when the changes are localized in a known part of the state space, state-of-the-art requires complete re-certification, which is particularly costly for neural certificates. We introduce VeRecycle, the first framework to formally reclaim guarantees for discrete-time stochastic dynamical systems. VeRecycle efficiently reuses probabilistic certificates when the system dynamics deviate only in a given subset of states. We present a general theoretical justification and algorithmic implementation. Our experimental evaluation shows scenarios where VeRecycle both saves significant computational effort and achieves competitive probabilistic guarantees in compositional neural control.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

27 of 45 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  4. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  5. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  6. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 151
  7. 2020Neural Lyapunov Controlcited by 142
  8. 2020Learning Stable Deep Dynamics Modelscited by 111
  9. 2018The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systemscited by 88
  10. 2024Marabou 2.0: A Versatile Formal Analyzer of Neural Networkscited by 81
  11. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  12. 2022Learning Control Policies for Stochastic Systems with Reach-avoid Guaranteescited by 23
15 more
  1. 2022Safety Certification for Stochastic Systems via Neural Barrier Functionscited by 22
  2. 2020Learning Dynamics Models with Stable Invariant Setscited by 18
  3. 2021Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systemscited by 17
  4. 2021Neural Termination Analysiscited by 16
  5. 2023Compositional Policy Learning in Stochastic Control Systems with Formal Guaranteescited by 14
  6. 2014Multiple-Environment Markov Decision Processescited by 13
  7. 2024Stochastic Omega-Regular Verification and Control with Supermartingalescited by 11
  8. 2021Scenario-Based Verification of Uncertain Parametric MDPscited by 8
  9. 2023When to Trust AI: Advances and Challenges for Certification of Neural Networkscited by 6
  10. 2022Learning Provably Stabilizing Neural Controllers for Discrete-Time Stochastic Systemscited by 5
  11. 2024Neural Continuous-Time Supermartingale Certificatescited by 5
  12. 2023Compositional Neural Certificates for Networked Dynamical Systemscited by 4
  13. 2023Verifiable Reinforcement Learning Systems via Compositionalitycited by 3
  14. 2024Data-driven Interval MDP for Robust Control Synthesiscited by 3
  15. 2022Safe Learning for Uncertainty-Aware Planning via Interval MDP Abstractioncited by 2

Built on by

Not cited yet.