About
I am an indefinite-term (tenured) Senior Research Scientist at RIKEN AIP and the deputy team director of the Adaptive Bayesian Intelligence Team. I am also 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 theory and practice of deep learning. I am currently interested in optimization and variational Bayesian principles to achieve this goal.
News
- 2026-09-28 Invited talk at the IAS Frontiers Conference on Geometry, Dynamics and Learning (Singapore).
- 2026-07-06 I will be at ICML 2026 (July 6-11) in Seoul!
- 2026-06-28 Attending ISBA 2026 from June 28 to July 3 in Nagoya, Japan for an invited talk.
- 2026-06-15 Attending the 4th Bayes-Duality Workshop from June 15-26.
- 2026-06-01 I am promoted to deputy team director of the Adaptive Bayesian Intelligence team.
- 2026-05-30 Visiting Munich until June 12; giving a tutorial at the Helmholtz AI Conference (HAICON26).
Selected Publications
-
SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks
Preprint, 2026. [code]
-
Log-Normal Multiplicative Dynamics for Stable Low-Precision Deep Learning
ICML, 2026.
-
Federated ADMM from Bayesian Duality
ICLR, 2026. [code]
-
Variational Learning is Effective for Large Deep Networks
ICML, 2024. [code]
-
SAM as an Optimal Relaxation of Bayes
ICLR, 2023. [code]
-
Proximal Backpropagation
ICLR, 2018. [code]