Thomas Möllenhoff

Postdoctoral Researcher
Approximate Bayesian Inference Team
RIKEN Center for Advanced Intelligence Project
Tokyo, Japan


thomas.moellenhoff (at) riken (dot) jp


I’m a researcher at the RIKEN Center for Advanced Intelligence Project and a member of the Approximate Bayesian Inference team where I work with Emtiyaz Khan. Before that, I completed my PhD in the Computer Vision & Artificial Intelligence group at TU Munich under the guidance of Daniel Cremers.

My current research focuses on the design and analysis of data-driven algorithms using ideas from mathematical optimization. Specifically, I’m interested in the following research areas:

  • Calculus of variations and geometric measure theory.
  • Optimal transport, information geometry.
  • (Bayesian) deep learning, variational inference.
  • Continuous optimization (convex and nonconvex).


  • Oct 20, 2020. New homepage is online.
  • Aug 13, 2020. I successfully defended my thesis and completed my PhD at TUM. Moving on, I am joining the Approximate Bayesian Inference Team in Tokyo as a postdoc!