About
I am an indefinite-term (tenured) Senior Research Scientist at RIKEN AIP, affiliated with the Adaptive Bayesian Intelligence Team and a core member of the Bayes-Duality project. Before, I was a postdoctoral researcher with Emtiyaz Khan. I completed my PhD in the Computer Vision Group at TU Munich with Daniel Cremers.
My research aims to advance both the theoretical understanding and practical performance of deep learning. I am currently interested in optimization and variational Bayesian principles to achieve this goal.
News
- 2026-01-30 One paper accepted at ICLR 2026 (Rio de Janeiro), and one paper accepted at CPAL 2026 (Tuebingen).
- 2025-12-12 I'm an area chair for ICML 2026.
- 2025-12-02 Attending NeurIPS in San Diego (presenting two posters).
- 2025-11-26 Invited talk at the RIKEN A*STAR (CFAR) Joint Workshop, Tokyo, Japan.
- 2025-11-13 Invited talk at the Singular Learning Theory Seminar (virtual).
- 2025-10-27 Attending a workshop on Bayesianism in the Age of Modern AI at MBZUAI, Abu Dhabi, UAE.
- 2025-10-17 I'm an area chair for ICLR 2026 and AISTATS 2026.
Selected Publications
- 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]
- 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]
- T. Möllenhoff, M. E. Khan. SAM as an Optimal Relaxation of Bayes. In Proceedings of the International Conference on Learning Representations (ICLR), 2023. [code]
- T. Frerix*, T. Möllenhoff*, M. Moeller*, D. Cremers. Proximal Backpropagation. In Proceedings of the International Conference on Learning Representations (ICLR), 2018. [code]