Monotone Neural Barrier Certificates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jafarpour, Saber, Nadali, Alireza, Trivedi, Ashutosh, Zamani, Majid
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915757183467520
author Jafarpour, Saber
Nadali, Alireza
Trivedi, Ashutosh
Zamani, Majid
author_facet Jafarpour, Saber
Nadali, Alireza
Trivedi, Ashutosh
Zamani, Majid
contents This report presents a neurosymbolic framework for safety verification and control synthesis in high-dimensional monotone dynamical systems without relying on explicit models or conservative Lipschitz bounds. The approach combines the expressiveness of neural networks with the rigor of symbolic reasoning via barrier certificates, functional analogs of inductive invariants that formally guarantee safety. Prior data-driven methods often treat dynamics as black-box models, relying on dense state-space discretization or Lipschitz overapproximations, leading to exponential sample complexity. In contrast, monotonicity--a pervasive structural property in many real-world systems--provides a symbolic scaffold that simplifies both learning and verification. Exploiting order preservation reduces verification to localized boundary checks, transforming a high-dimensional problem into a tractable, low-dimensional one. Barrier certificates are synthesized using monotone neural network architectures with embedded monotonicity constraints--trained via gradient-based optimization guided by barrier conditions. This enables scalable, formally sound verification directly from simulation data, bridging black-box learning and formal guarantees within a unified neurosymbolic framework.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12178
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Monotone Neural Barrier Certificates
Jafarpour, Saber
Nadali, Alireza
Trivedi, Ashutosh
Zamani, Majid
Systems and Control
This report presents a neurosymbolic framework for safety verification and control synthesis in high-dimensional monotone dynamical systems without relying on explicit models or conservative Lipschitz bounds. The approach combines the expressiveness of neural networks with the rigor of symbolic reasoning via barrier certificates, functional analogs of inductive invariants that formally guarantee safety. Prior data-driven methods often treat dynamics as black-box models, relying on dense state-space discretization or Lipschitz overapproximations, leading to exponential sample complexity. In contrast, monotonicity--a pervasive structural property in many real-world systems--provides a symbolic scaffold that simplifies both learning and verification. Exploiting order preservation reduces verification to localized boundary checks, transforming a high-dimensional problem into a tractable, low-dimensional one. Barrier certificates are synthesized using monotone neural network architectures with embedded monotonicity constraints--trained via gradient-based optimization guided by barrier conditions. This enables scalable, formally sound verification directly from simulation data, bridging black-box learning and formal guarantees within a unified neurosymbolic framework.
title Monotone Neural Barrier Certificates
topic Systems and Control
url https://arxiv.org/abs/2508.12178