Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Maaz, Muhammad, Chan, Timothy C. Y.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.15767
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918016693829632
author Maaz, Muhammad
Chan, Timothy C. Y.
author_facet Maaz, Muhammad
Chan, Timothy C. Y.
contents We introduce the problem of formally verifying properties of Markov processes where the parameters are given by the output of machine learning models. For a broad class of machine learning models, including linear models, tree-based models, and neural networks, verifying properties of Markov chains like reachability, hitting time, and total reward can be formulated as a bilinear program. We develop a decomposition and bound propagation scheme for solving the bilinear program and show through computational experiments that our method solves the problem to global optimality up to 100x faster than state-of-the-art solvers. To demonstrate the practical utility of our approach, we apply it to a real-world healthcare case study. Along with the paper, we release markovml, an open-source tool for building Markov processes, integrating pretrained machine learning models, and verifying their properties, available at https://github.com/mmaaz-git/markovml.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15767
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Formal Verification of Markov Processes with Learned Parameters
Maaz, Muhammad
Chan, Timothy C. Y.
Machine Learning
Artificial Intelligence
Optimization and Control
68Q60 (primary) 90C30, 60J20, 60J22 (secondary)
F.4.1; G.1.6; I.2.3
We introduce the problem of formally verifying properties of Markov processes where the parameters are given by the output of machine learning models. For a broad class of machine learning models, including linear models, tree-based models, and neural networks, verifying properties of Markov chains like reachability, hitting time, and total reward can be formulated as a bilinear program. We develop a decomposition and bound propagation scheme for solving the bilinear program and show through computational experiments that our method solves the problem to global optimality up to 100x faster than state-of-the-art solvers. To demonstrate the practical utility of our approach, we apply it to a real-world healthcare case study. Along with the paper, we release markovml, an open-source tool for building Markov processes, integrating pretrained machine learning models, and verifying their properties, available at https://github.com/mmaaz-git/markovml.
title Formal Verification of Markov Processes with Learned Parameters
topic Machine Learning
Artificial Intelligence
Optimization and Control
68Q60 (primary) 90C30, 60J20, 60J22 (secondary)
F.4.1; G.1.6; I.2.3
url https://arxiv.org/abs/2501.15767