List of Publications

preprints

1. T. Papamarkou, ..., T. Möllenhoff, ... (with many authors), Position: Agentic AI Systems should be making Bayes-Consistent Decisions, preprint, 2026.
2. N. Daheim, T. Möllenhoff, M. Liang Ang, M. E. Khan, SVRG and Beyond via Posterior Correction, preprint, 2025.
3. K. Nishida, E. M. Kiral, K. Bannai, M. E. Khan, T. Möllenhoff. Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks, preprint, 2025.
4. B. Cong, N. Daheim, Y. Shen, R. Yokota, M. E. Khan, T. Möllenhoff. Improving LoRA with Variational Learning, preprint, 2025.
5. H. Monzón Maldonado, T. Möllenhoff, N. Daheim, I. Gurevych, M. E. Khan. How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging, preprint, 2025.

published

6. T. Möllenhoff*, S. Swaroop*, F. Doshi-Velez, M. E. Khan. Federated ADMM from Bayesian Duality, In Proceedings of the International Conference on Learning Representations (ICLR), 2026. [code]
7. S. Sklaviadis, T. Möllenhoff, M. A. T. Figueiredo, A. Martins, M. E. Khan. A Stein identity for q-Gaussians with bounded support, In Proceedings of the Conference on Parsimony and Learning (CPAL), 2026.
8. T. Le Minh, J. Arbel, T. Möllenhoff, M. E. Khan, F. Forbes. Natural Variational Annealing for Multimodal Optimization, Information and Inference: A Journal of the IMA, 2026.

9. A. Ghosh, B. Cong, R. Yokota, S. Ravishankar, R. Wang, M. Tao, M. E. Khan, T. Möllenhoff. Variational Learning Finds Flatter Solutions at the Edge of Stability, Neural Information Processing Systems (NeurIPS), 2025.
10. Y. Jung, H. Lee, W. Chen, T. Möllenhoff, Y. Li, J. Lee, M. E. Khan. Compact Memory for Continual Logistic Regression, Neural Information Processing Systems (NeurIPS), 2025.
11. N. Kumar, T. Möllenhoff, M. E. Khan, A. Lucchi. Optimization Guarantees for Square-Root Natural-Gradient Variational Inference, Transactions on Machine Learning Research (TMLR), 2025.
12. N. Daheim, C. Meister, T. Möllenhoff, I. Gurevych. Uncertainty-Aware Decoding with Minimum Bayes' Risk, In Proceedings of the International Conference on Learning Representations (ICLR), 2025.

13. B. Cong, N. Daheim, Y. Shen, D. Cremers, R. Yokota, M.E. Khan, T. Möllenhoff. Variational Low-Rank Adaptation using IVON. NeurIPS Workshop on Fine-Tuning in Modern ML (FITML), 2024. [code]
14. Y. Shen*, N. Daheim*, B. Cong, P. Nickl, G.M. Marconi, C. Bazan, R. Yokota, I. Gurevych, D. Cremers, M.E. Khan, T. Möllenhoff. Variational Learning is Effective for Large Deep Networks. In Proceedings of the International Conference on Machine Learning (ICML), 2024. [code]
15. N. Daheim, T. Möllenhoff, E. M. Ponti, I. Gurevych, M. E. Khan. Model Merging by Uncertainty-Based Gradient Matching. In Proceedings of the International Conference on Learning Representations (ICLR), 2024. [code]
16. E. Guha, S. Natarajan, T. Möllenhoff, M. E. Khan, E. Ndiaye. Conformal Prediction via Regression-as-Classification. In Proceedings of the International Conference on Learning Representations (ICLR), 2024. [code]

17. P. Nickl, L. Xu, D. Tailor, T. Möllenhoff, M. E. Khan. The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data. In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2023. [code]
18. T. Möllenhoff, M. E. Khan. SAM as an Optimal Relaxation of Bayes. In Proceedings of the International Conference on Learning Representations (ICLR), 2023. [code]
19. E. M. Kiral, T. Möllenhoff, M. E. Khan. The Lie-Group Bayesian Learning Rule. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. [code]
20. Z. Ye, B. Haefner, Y. Quéau, T. Möllenhoff, D. Cremers. A Cutting-Plane Method for Sublabel-Accurate Relaxation of Problems with Product Label Spaces, International Journal of Computer Vision (IJCV), 2023.

21. H. Dröge, T. Möllenhoff, M. Moeller. Non-Smooth Energy Dissipating Networks. IEEE Conference on Image Processing (ICIP), 2022.
22. H. Bauermeister*, E. Laude*, T. Möllenhoff, M. Moeller, D. Cremers. Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields. SIAM Journal on Imaging Sciences, 2022. [published version]

23. Z. Ye, B. Haefner, Y. Quéau, T. Möllenhoff, D. Cremers. Sublabel-Accurate Multilabeling Meets Product Label Spaces. In Proceedings of the DAGM German Conference on Pattern Recognition (GCPR), 2021.

24. T. Möllenhoff. Efficient Lifting Methods for Variational Problems. PhD Thesis, Technical University of Munich, 2020.
25. Z. Ye, T. Möllenhoff, T. Wu, D. Cremers. Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. [code]

26. P. Bréchet, T. Wu, T. Möllenhoff, D. Cremers. Informative GANs via structured regularization of optimal transport. Optimal Transport and Machine Learning (NeurIPS Workshop), 2019.
27. T. Möllenhoff, D. Cremers. Lifting vectorial variational problems: A natural formulation based on geometric measure theory and discrete exterior calculus. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [talk]
28. T. Möllenhoff, D. Cremers. Flat metric minimization with applications in generative modeling. In Proceedings of the International Conference on Machine Learning (ICML), 2019. [code], [talk], [poster]
29. M. Moeller, T. Möllenhoff, D. Cremers. Controlling neural networks via energy dissipation. In Proceedings of the International Conference on Computer Vision (ICCV), 2019.

30. B. Haefner, T. Möllenhoff, Y. Quéau, D. Cremers. Fight ill-posedness with ill-posedness: Single-shot variational depth super-resolution from shading. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [code]
31. T. Frerix*, T. Möllenhoff*, M. Moeller*, D. Cremers. Proximal backpropagation. In Proceedings of the International Conference on Learning Representations (ICLR), 2018. [code]
32. T. Möllenhoff, Z. Ye, T. Wu, D. Cremers. Combinatorial preconditioners for proximal algorithms on graphs. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2018.

33. T. Möllenhoff, D. Cremers. Sublabel-accurate discretization of nonconvex free-discontinuity problems. In Proceedings of the International Conference on Computer Vision (ICCV), 2017.

34. E. Laude*, T. Möllenhoff*, M. Moeller, J. Lellmann, D. Cremers. Sublabel-accurate convex relaxation of vectorial multilabel energies. In Proceedings of the European Conference on Computer Vision (ECCV), 2016. [code]
35. T. Möllenhoff*, E. Laude*, M. Moeller, J. Lellmann, D. Cremers. Sublabel-accurate relaxation of nonconvex energies. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [code], [talk]

36. T. Möllenhoff, E. Strekalovskiy, M. Moeller, D. Cremers. The primal-dual hybrid gradient method for semiconvex splittings. SIAM Journal on Imaging Sciences, 2015. [talk], [slides]
37. T. Möllenhoff, E. Strekalovskiy, M. Moeller, D. Cremers. Low rank priors for color image regularization. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), 2015.

38. T. Möllenhoff, E. Toeppe, C. Nieuwenhuis, D. Cremers. Efficient convex optimization for minimal partition problems with volume constraints. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), 2013.