---
res:
  bibo_abstract:
  - Active learning of physical systems must commonly respect practical safety constraints,
    which restricts the exploration of the design space. Gaussian Processes (GPs)
    and their calibrated uncertainty estimations are widely used for this purpose.
    In many technical applications the design space is explored via continuous trajectories,
    along which the safety needs to be assessed. This is particularly challenging
    for strict safety requirements in GP methods, as it employs computationally expensive
    Monte-Carlo sampling of high quantiles. We address these challenges by providing
    provable safety bounds based on the adaptively sampled median of the supremum
    of the posterior GP. Our method significantly reduces the number of samples required
    for estimating high safety probabilities, resulting in faster evaluation without
    sacrificing accuracy and exploration speed. The effectiveness of our safe active
    learning approach is demonstrated through extensive simulations and validated
    using a real-world engine example.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Jörn
      foaf_name: Tebbe, Jörn
      foaf_surname: Tebbe
      foaf_workInfoHomepage: http://www.librecat.org/personId=85958
  - foaf_Person:
      foaf_givenName: Christoph
      foaf_name: Zimmer, Christoph
      foaf_surname: Zimmer
  - foaf_Person:
      foaf_givenName: Ansgar
      foaf_name: Steland, Ansgar
      foaf_surname: Steland
  - foaf_Person:
      foaf_givenName: Markus
      foaf_name: Lange-Hegermann, Markus
      foaf_surname: Lange-Hegermann
      foaf_workInfoHomepage: http://www.librecat.org/personId=71761
  - foaf_Person:
      foaf_givenName: Fabian
      foaf_name: Mies, Fabian
      foaf_surname: Mies
  dct_date: 2024^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2640-3498
  dct_language: eng
  dct_publisher: MLResearchPress @
  dct_title: Efficiently Computable Safety Bounds for Gaussian Processes in Active
    Learning@
...