Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lange-Hegermann, Markus, Zimmer, Christoph
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912330114138112
author Lange-Hegermann, Markus
Zimmer, Christoph
author_facet Lange-Hegermann, Markus
Zimmer, Christoph
contents Experimental exploration of high-cost systems with safety constraints, common in engineering applications, is a challenging endeavor. Data-driven models offer a promising solution, but acquiring the requisite data remains expensive and is potentially unsafe. Safe active learning techniques prove essential, enabling the learning of high-quality models with minimal expensive data points and high safety. This paper introduces a safe active learning framework tailored for time-varying systems, addressing drift, seasonal changes, and complexities due to dynamic behavior. The proposed Time-aware Integrated Mean Squared Prediction Error (T-IMSPE) method minimizes posterior variance over current and future states, optimizing information gathering also in the time domain. Empirical results highlight T-IMSPE's advantages in model quality through toy and real-world examples. State of the art Gaussian processes are compatible with T-IMSPE. Our theoretical contributions include a clear delineation which Gaussian process kernels, domains, and weighting measures are suitable for T-IMSPE and even beyond for its non-time aware predecessor IMSPE.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10581
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes
Lange-Hegermann, Markus
Zimmer, Christoph
Machine Learning
Artificial Intelligence
Optimization and Control
Probability
I.2.6; G.3; J.2; I.1.4
Experimental exploration of high-cost systems with safety constraints, common in engineering applications, is a challenging endeavor. Data-driven models offer a promising solution, but acquiring the requisite data remains expensive and is potentially unsafe. Safe active learning techniques prove essential, enabling the learning of high-quality models with minimal expensive data points and high safety. This paper introduces a safe active learning framework tailored for time-varying systems, addressing drift, seasonal changes, and complexities due to dynamic behavior. The proposed Time-aware Integrated Mean Squared Prediction Error (T-IMSPE) method minimizes posterior variance over current and future states, optimizing information gathering also in the time domain. Empirical results highlight T-IMSPE's advantages in model quality through toy and real-world examples. State of the art Gaussian processes are compatible with T-IMSPE. Our theoretical contributions include a clear delineation which Gaussian process kernels, domains, and weighting measures are suitable for T-IMSPE and even beyond for its non-time aware predecessor IMSPE.
title Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes
topic Machine Learning
Artificial Intelligence
Optimization and Control
Probability
I.2.6; G.3; J.2; I.1.4
url https://arxiv.org/abs/2405.10581