Approximate Bayesian Inference Team
RIKEN Center for Advanced Intelligence Project
thomas.moellenhoff (at) riken (dot) jp
CV – Scholar – github – Twitter
I’m a research scientist at the RIKEN Center for Advanced Intelligence Project, affiliated with the Approximate Bayesian Inference team and a core member of the Bayes Duality project. Before that, I was a postdoctoral researcher working with Emtiyaz Khan. I completed my PhD in the Computer Vision Group at TU Munich under the guidance of Daniel Cremers.
My current research focuses on the design and analysis of new algorithms to improve deep learning via Bayesian principles, with the aim to develop methods that are robust, adaptable and more interpretable.
- Jul 22 - 29, 2023. I’ll be attending ICML in Hawaii, reach out if you want to catch up or have a chat!
- May 25, 2023. I gave two invited lectures on Bayesian deep learning at UNIST AI graduate school and at SungKyunKwan University.
- May 24, 2023. The deadline for our ICML 2023 workshop on duality principles for modern ML has been extended until May 29th, anywhere on earth.
- April 7, 2023. The call for papers for our ICML 2023 workshop on duality principles for modern ML is out now!
- April 1, 2023. I got promoted, and am now a tenured research scientist at RIKEN. Thanks to all my collaborators who made this possible!
- Mar 17, 2023. Our workshop on ‘Duality Principles in Modern Machine Learning’ got accepted at ICML 2023.
- Mar 15 - 19, 2023. I am visiting the Computer Vision Group at TU Munich.
- Mar 11, 2023. I will be at the joint Vietnam-Japan AI Workshop (April 20 – April 22), at AISTATS in Valencia (April 25 – April 28) and at ICLR in Kigali (May 1 – May 5). Please reach out if you want to meet up for a chat.
- Mar 7, 2023. I gave a talk at the Optimization and Machine Learning Systems Group, visiting Aurelien Lucci in Basel.
- Feb 7, 2023. I am giving talks on SAM as an Optimal Relaxation of Bayes at EPFL (March 10) and the Optimization and Machine Learning Workshop in Nuremberg (March 14).
- Feb 6, 2023. Got top reviewer award (top 10%) for AISTATS ‘23!
- Jan 21, 2023. Our paper on SAM as an Optimal Relaxation of Bayes got accepted at ICLR 2023 (notable top-5%).
- Jan 20, 2023. Our paper on The Lie-Group Bayesian Learning Rule is accepted at AISTATS 2023.
- Dec 15, 2022. I gave a talk on SAM as an Optimal Relaxation of Bayes at the Optimization, Systems and Control Group at KU Leuven.
- Oct 31, 2022. I’ll be giving talks on Nov 1st, 10:50 - 11:40 JST in the ABI Team Seminar and on Dec 8th, 23:00 - 24:00 JST at the Mathematical Optimization Group in Tübingen. More talks to be announced soon!
- Oct 5, 2022. New preprint available: SAM as an Optimal Relaxation of Bayes!
See older news.