Profil Dr. Stefanie Schwaar


  • Analyse und Prognose von Zeitreihen
  • Nicht-lineare Regressionsmodelle 
  • Change-point Analyse
  • Machine Learning Methoden



  • Sicks, R.; Korn, R.; Schwaar, S.:
    A Generalised Linear Model Framework for β-Variational Autoencoders based on Exponential Dispersion Families.
    Journal of Machine Learning Research, Volume 22, Pages 1-41, (2021).
  • Blandfort, F.; Glock, C.; Sass, J.; Sefrin, S.; Schwaar, S.:
    Efficient and Comprehensive Time-Dependent Reliability Analysis of Complex Structures by a Parameter State Model.
    ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering, 7(2), (2021).
  • Franke, J.; Hefter M.; Herzwurm A.; Ritter K.; Schwaar, S.:
    Adaptive Quantile Computation for Brownian Bridge in Change-Point Analysis.
    (akzeptiert in Computational Statistics and Data Analysis,, (2020).
  • Schwaar, S.:
    Data-driven Change-Point Test and Estimator., (2020).
  • Sicks, R.; Korn R.; Schwaar S.:
    A lower bound for the ELBO of the Bernoulli Variational Autoencoder., (2020).
  • Blandfort, F.; Glock, C.; Sass, J.; Sefrin, S.; Schwaar, S.:
    Subset Simulation Interpolation - A New Approach to Compute Effects of Model-Dynamics in Structural Reliability.
    29th European Safety and Reliability Conference (ESREL2019), Hannover, (2019).
  • Blandfort, F.; Glock, C.; Sass, J.; Sefrin, S.; Schwaar, S.:
    A Parametric State Space Model for Time-Dependent Reliability Analysis.
    Accepted for 17th International Probabilistic Workshop (IPW2019), Edinburgh, (2019).
  • Dresvyanskiy, D.; Karaseva, T.; Mitrofanov, S.; Redenbach, C.; Makogin, V.; Spodarev, E.; Schwaar, S.:
    Application of Clustering Methods to Anomaly Detection in Fibrous Media.
    IOP Conference Series: Materials Science and Engineering, Vol. 537 (2), p.022001, (2019).
  • Schwaar, S.:
    Asymptotics for change-point tests and change-point estimators.
    Dissertation, TU Kaiserslautern, (2017).

Sammlung der Publikationen von Stefanie Schwaar in der Fraunhofer-Publica