Publications

A list of publications can be also found on Google Scholar. * denotes equal contribution.

2024

    Differentiable Annealed Importance Sampling Minimizes The Symmetrized Kullback-Leibler Divergence Between Initial and Target Distribution.
    Johannes Zenn, and Robert Bamler
    In Forty-first International Conference on Machine Learning (ICML), 2024.
     Paper     GitHub     Copy BibTex 

2023

    The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch.
    Tim Z. Xiao*, Johannes Zenn*, and Robert Bamler
    In NeurIPS 2023 Workshop on Distribution Shifts, 2023.
     Paper     Project Page     Copy BibTex 

    Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers.
    Johannes Zenn, and Robert Bamler
    In International Conference on Learning Representations, Tiny Papers, 2023.
     Paper     GitHub     Poster     Copy BibTex 

2021

    ProbNum: Probabilistic Numerics in Python.
    Jonathan Wenger, Nicholas Krämer, Marvin Pförtner, Jonathan Schmidt, Nathanael Bosch, Nina Effenberger, Johannes Zenn, Alexandra Gessner, Toni Karvonen, François-Xavier Briol, Maren Mahsereci, and Philipp Hennig
    In arXiv preprint arXiv:2112.02100, 2021.
     Paper     GitHub     Copy BibTex