Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching.

Paul Hagemann

Jannis Chemseddine Paul Hagemann Gabriele Steidl Christian Wald Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching. 141:1-141:47 2025 26 J. Mach. Learn. Res. https://jmlr.org/papers/v26/24-0586.html db/journals/jmlr/jmlr26.html#ChemseddineHSW25

Paul Hagemann Sophie Mildenberger Lars Ruthotto Gabriele Steidl Nicole Tianjiao Yang Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation. 2025 1337-1366 7 SIAM J. Math. Data Sci. 3 https://doi.org/10.1137/23m1614092 db/journals/simods/simods7.html#HagemannMRSY25 streams/journals/simods

Ségolène Tiffany Martin Anne Gagneux Paul Hagemann Gabriele Steidl PnP-Flow: Plug-and-Play Image Restoration with Flow Matching. 2025 ICLR https://openreview.net/forum?id=5AtHrq3B5R conf/iclr/2025 db/conf/iclr/iclr2025.html#MartinGHS25 Paul Hagemann Janina Schütte David Sommer Martin Eigel Gabriele Steidl Sampling from Boltzmann Densities with Physics Informed Low-Rank Formats. 374-386 2025 SSVM (1) https://doi.org/10.1007/978-3-031-92366-1_29 conf/scalespace/2025-1 db/conf/scalespace/ssvm2025-1.html#HagemannSSES25 streams/conf/scalespace

T. Jahn Jannis Chemseddine Paul Hagemann Christian Wald Gabriele Steidl Trajectory Generator Matching for Time Series. 2025 May abs/2505.23215 CoRR https://doi.org/10.48550/arXiv.2505.23215 db/journals/corr/corr2505.html#abs-2505-23215 streams/journals/corr

Paul Hagemann Robert Gruhlke Bernhard Stankewitz Claudia Schillings Gabriele Steidl Provable Mixed-Noise Learning with Flow-Matching. 2025 August abs/2508.18122 CoRR https://doi.org/10.48550/arXiv.2508.18122 db/journals/corr/corr2508.html#abs-2508-18122 streams/journals/corr

Paul Hagemann Simon Müller Janine George Philipp Benner Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models. 2025 December abs/2512.09514 CoRR https://doi.org/10.48550/arXiv.2512.09514 db/journals/corr/corr2512.html#abs-2512-09514 streams/journals/corr

Paul Hagemann Johannes Hertrich Maren Casfor Sebastian Heidenreich Gabriele Steidl Mixed noise and posterior estimation with conditional deepGEM. 35001 2024 5 Mach. Learn. Sci. Technol. 3 https://doi.org/10.1088/2632-2153/ad5926 db/journals/mlst/mlst5.html#HagemannHCHS24

Paul Hagemann Johannes Hertrich Fabian Altekrüger Robert Beinert Jannis Chemseddine Gabriele Steidl Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel. 2024 ICLR https://openreview.net/forum?id=YrXHEb2qMb conf/iclr/2024 db/conf/iclr/iclr2024.html#HagemannHABCS24 Johannes Hertrich Christian Wald Fabian Altekrüger Paul Hagemann Generative Sliced MMD Flows with Riesz Kernels. 2024 ICLR https://openreview.net/forum?id=VdkGRV1vcf conf/iclr/2024 db/conf/iclr/iclr2024.html#HertrichWAH24

Paul Hagemann Johannes Hertrich Maren Casfor Sebastian Heidenreich Gabriele Steidl Mixed Noise and Posterior Estimation with Conditional DeepGEM. 2024 abs/2402.02964 CoRR https://doi.org/10.48550/arXiv.2402.02964 db/journals/corr/corr2402.html#abs-2402-02964

Jannis Chemseddine Paul Hagemann Christian Wald Gabriele Steidl Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching. 2024 abs/2403.18705 CoRR https://doi.org/10.48550/arXiv.2403.18705 db/journals/corr/corr2403.html#abs-2403-18705

Ségolène Martin Anne Gagneux Paul Hagemann Gabriele Steidl PnP-Flow: Plug-and-Play Image Restoration with Flow Matching. 2024 abs/2410.02423 CoRR https://doi.org/10.48550/arXiv.2410.02423 db/journals/corr/corr2410.html#abs-2410-02423 streams/journals/corr

Paul Hagemann Janina Schütte David Sommer Martin Eigel Gabriele Steidl Sampling from Boltzmann densities with physics informed low-rank formats. 2024 abs/2412.07637 CoRR https://doi.org/10.48550/arXiv.2412.07637 db/journals/corr/corr2412.html#abs-2412-07637 streams/journals/corr

Fabian Altekrüger Paul Hagemann Gabriele Steidl Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems. 2023 2023 Trans. Mach. Learn. Res. https://openreview.net/forum?id=Wcui061fxr db/journals/tmlr/tmlr2023.html#AltekrugerHS23

Paul Hagemann Lars Ruthotto Gabriele Steidl Nicole Tianjiao Yang Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation. 2023 abs/2303.04772 CoRR https://doi.org/10.48550/arXiv.2303.04772 db/journals/corr/corr2303.html#abs-2303-04772

Fabian Altekrüger Paul Hagemann Gabriele Steidl Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems. 2023 abs/2303.15845 CoRR https://doi.org/10.48550/arXiv.2303.15845 db/journals/corr/corr2303.html#abs-2303-15845

Johannes Hertrich Christian Wald Fabian Altekrüger Paul Hagemann Generative Sliced MMD Flows with Riesz Kernels. 2023 abs/2305.11463 CoRR https://doi.org/10.48550/arXiv.2305.11463 db/journals/corr/corr2305.html#abs-2305-11463

Jannis Chemseddine Paul Hagemann Christian Wald Y-Diagonal Couplings: Approximating Posteriors with Conditional Wasserstein Distances. 2023 abs/2310.13433 CoRR https://doi.org/10.48550/arXiv.2310.13433 db/journals/corr/corr2310.html#abs-2310-13433

Moritz Piening Fabian Altekrüger Johannes Hertrich Paul Hagemann Andrea Walther Gabriele Steidl Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction. 2023 abs/2312.16611 CoRR https://doi.org/10.48550/arXiv.2312.16611 db/journals/corr/corr2312.html#abs-2312-16611

Paul Hagemann Johannes Hertrich Gabriele Steidl Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint. 1162-1190 2022 March 10 SIAM/ASA J. Uncertain. Quantification 1 https://doi.org/10.1137/21m1450604 db/journals/juq/juq10.html#HagemannHS22

Fabian Altekrüger Alexander Denker Paul Hagemann Johannes Hertrich Peter Maass Gabriele Steidl PatchNR: Learning from Small Data by Patch Normalizing Flow Regularization. 2022 abs/2205.12021 CoRR https://doi.org/10.48550/arXiv.2205.12021 db/journals/corr/corr2205.html#abs-2205-12021

Anna Andrle Nando Farchmin Paul Hagemann Sebastian Heidenreich Victor Soltwisch Gabriele Steidl Invertible Neural Networks Versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence. 528-539 2021 SSVM https://doi.org/10.1007/978-3-030-75549-2_42 conf/scalespace/2021 db/conf/scalespace/ssvm2021.html#AndrleFHHSS21

Anna Andrle Nando Farchmin Paul Hagemann Sebastian Heidenreich Victor Soltwisch Gabriele Steidl Invertible Neural Networks versus MCMC for Posterior Reconstruction in Grazing Incidence X-Ray Fluorescence. 2021 abs/2102.03189 CoRR https://arxiv.org/abs/2102.03189 db/journals/corr/corr2102.html#abs-2102-03189

Paul Hagemann Johannes Hertrich Gabriele Steidl Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint. 2021 abs/2109.11375 CoRR https://arxiv.org/abs/2109.11375 db/journals/corr/corr2109.html#abs-2109-11375

Johannes Hertrich Paul Hagemann Gabriele Steidl A Unified Approach to Variational Autoencoders and Stochastic Normalizing Flows via Markov Chains. 2021 abs/2111.12506 CoRR https://arxiv.org/abs/2111.12506 db/journals/corr/corr2111.html#abs-2111-12506

Paul Hagemann Sebastian Neumayer Stabilizing Invertible Neural Networks Using Mixture Models. 2020 abs/2009.02994 CoRR https://arxiv.org/abs/2009.02994 db/journals/corr/corr2009.html#abs-2009-02994

Fabian Altekrüger Anna Andrle Robert Beinert Philipp Benner Maren Casfor Jannis Chemseddine Alexander Denker Martin Eigel Anne Gagneux Janine George Robert Gruhlke Nando HegemannNando Farchmin Sebastian Heidenreich Johannes Hertrich T. Jahn Peter Maass Ségolène MartinSégolène Tiffany Martin Sophie Mildenberger Simon Müller Sebastian Neumayer Moritz Piening Lars Ruthotto Claudia Schillings Janina Schütte Victor Soltwisch David Sommer Bernhard Stankewitz Gabriele Steidl Christian Wald Andrea Walther Nicole Tianjiao Yang