About me

I am a Post-doctoral researcher at Technical University Berlin in the group of Gabriele Steidl with research interests in Generative modeling, flow matching, curves in probability space and the application of stochastic processes in machine learning.

Publications

Neural sampling from Boltzmann densities: Fisher-Rao curves in the Wasserstein geometry.
Jannis Chemseddine, Christian Wald, Richard Duong, Gabriele Steidl (2025).
International Conference on Learning Representations (ICLR) [openreview],[arxiv]

Trajectory Generator Matching for Time Series.
T. Jahn, J. Chemseddine, P. Hagemann, C. Wald, G. Steidl (2025).
[arxiv]

Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans.
Christian Wald, Gabriele Steidl (Springer 2025).
[Springer],[arxiv]

Conditional wasserstein distances with applications in bayesian ot flow matching.
Jannis Chemseddine, Paul Hagemann, Gabriele Steidl, Christian Wald (JMLR 2025).
[JMLR],[arxiv]

A study of particle motion in the presence of clusters.
Christian Wald, Gabriele Steidl (2025).
Communications in Statistics-Simulation and Computation

Generative sliced MMD flows with Riesz kernels.
Johannes Hertrich, Christian Wald, Fabian Altekrüger, Paul Hagemann (2024).
International Conference on Learning Representations 2024
[openreview], [arxiv], [code]

Active Learning with the nnUNet and Sample Selection with Uncertainty-Aware Submodular Mutual Information Measure.
Bernhard Föllmer, Kenrick Schulze, Christian Wald, Sebastian Stober, Wojciech Samek, Marc Dewey (2024).
Medical Imaging with Deep Learning

Sparse additive function decompositions facing basis transforms.
Fatima Antarou Ba, Oleh Melnyk, Christian Wald, Gabriele Steidl (2024).
Foundations of Data Science. [arxiv]

Joint reconstruction and segmentation in undersampled 3D knee MRI combining shape knowledge and deep learning.
Andreas Kofler, Christian Wald, Christoph Kolbitsch, C. V. Tycowicz, Felix Ambellan (2024).
Physics in Medicine & Biology [iopscience]

Y-Diagonal couplings: Approximating posteriors with conditional Wasserstein distances.
Jannis Chemseddine, Paul Hagemann, Christian Wald (2023).
[arxiv]

Active multitask learning with uncertainty-weighted loss for coronary calcium scoring.
Bernhard Föllmer, Federico Biavati, Christian Wald, Sebastian Stober, Jackie Ma, Marc Dewey, Wojciech Samek (2022).
Medical physics [aapm]

Convolutional dictionary learning by end-to-end training of iterative neural networks.
Andreas Kofler, Christian Wald, Tobias Schaeffter, Markus Haltmeier, Christoph Kolbitsch (2022).
2022 30th European Signal Processing Conference (EUSIPCO)

Convolutional analysis operator learning by end-to-end training of iterative neural networks.
Andreas Kofler, Christian Wald, Tobias Schaeffter, Markus Haltmeier, Christoph Kolbitsch (2022).
2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)

Neural networks-based regularization for large-scale medical image reconstruction.
Andreas Kofler, Markus Haltmeier, Tobias Schaeffter, Marc Kachelrieß, Marc Dewey, Christian Wald, Christoph Kolbitsch (2020).
Physics in Medicine & Biology

Spatio-temporal deep learning-based undersampling artefact reduction for 2D radial cine MRI with limited training data.
Andreas Kofler, Marc Dewey, Tobias Schaeffter, Christian Wald, Christoph Kolbitsch (2019).
IEEE transactions on medical imaging

A p-adic quantum group and the quantized p-adic upper half plane.
Christian Wald (2017).
[PHD Thesis edoc HU]