Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Zhouxing, Li, Haoyu, Hsieh, Cho-Jui, Zhang, Huan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915916788269056
author Shi, Zhouxing
Li, Haoyu
Hsieh, Cho-Jui
Zhang, Huan
author_facet Shi, Zhouxing
Li, Haoyu
Hsieh, Cho-Jui
Zhang, Huan
contents We study the problem of learning verifiably Lyapunov-stable neural controllers that provably satisfy the Lyapunov asymptotic stability condition within a region-of-attraction (ROA). Unlike previous works that adopted counterexample-guided training without considering the computation of verification in training, we introduce Certified Training with Branch-and-Bound (CT-BaB), a new certified training framework that optimizes certified bounds, thereby reducing the discrepancy between training and test-time verification that also computes certified bounds. To achieve a relatively global guarantee on an entire input region-of-interest, we propose a training-time BaB technique that maintains a dynamic training dataset and adaptively splits hard input subregions into smaller ones, to tighten certified bounds and ease the training. Meanwhile, subregions created by the training-time BaB also inform test-time verification, for a more efficient training-aware verification. We demonstrate that CT-BaB yields verification-friendly models that can be more efficiently verified at test time while achieving stronger verifiable guarantees with larger ROA. On the largest output-feedback 2D Quadrotor system experimented, CT-BaB reduces verification time by over 11X relative to the previous state-of-the-art baseline using Counterexample Guided Inductive Synthesis (CEGIS), while achieving 164X larger ROA. Code is available at https://github.com/shizhouxing/CT-BaB.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18235
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control
Shi, Zhouxing
Li, Haoyu
Hsieh, Cho-Jui
Zhang, Huan
Machine Learning
Artificial Intelligence
Robotics
Systems and Control
We study the problem of learning verifiably Lyapunov-stable neural controllers that provably satisfy the Lyapunov asymptotic stability condition within a region-of-attraction (ROA). Unlike previous works that adopted counterexample-guided training without considering the computation of verification in training, we introduce Certified Training with Branch-and-Bound (CT-BaB), a new certified training framework that optimizes certified bounds, thereby reducing the discrepancy between training and test-time verification that also computes certified bounds. To achieve a relatively global guarantee on an entire input region-of-interest, we propose a training-time BaB technique that maintains a dynamic training dataset and adaptively splits hard input subregions into smaller ones, to tighten certified bounds and ease the training. Meanwhile, subregions created by the training-time BaB also inform test-time verification, for a more efficient training-aware verification. We demonstrate that CT-BaB yields verification-friendly models that can be more efficiently verified at test time while achieving stronger verifiable guarantees with larger ROA. On the largest output-feedback 2D Quadrotor system experimented, CT-BaB reduces verification time by over 11X relative to the previous state-of-the-art baseline using Counterexample Guided Inductive Synthesis (CEGIS), while achieving 164X larger ROA. Code is available at https://github.com/shizhouxing/CT-BaB.
title Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control
topic Machine Learning
Artificial Intelligence
Robotics
Systems and Control
url https://arxiv.org/abs/2411.18235