Postdoctoral Position in Approximate Bayesian Inference / Advanced Image Processing

Postdoctoral Position in Approximate Bayesian Inference / Advanced Image Processing

Posted by Rebecca Martin on Mon, 15/11/2010 - 15:43

EPFL's newly established Probabilistic Machine Learning Lab
( has an opening for a post-doctoral fellow in the
field of Bayesian machine learning / computer vision. The initial appointment
is for 12 months, extensions up to 3 years are possible. Topics of interest

- Variational approximate Bayesian inference, particularly in large scale
generalized linear model settings
- Structured image modelling. Inference over sequences (stacks) of image
frames, with particular emphasis on parallel computing (applications in
medical imaging, computer vision, and elsewhere)
- Applications to adaptive compressive sensing, medical imaging, and low-level
computer vision, among others
- Theoretical analysis of variational inference approximations and Bayesian
adaptive compressive sensing


The Probabilistic ML laboratory offers the chance for seminal work to
establish approximate Bayesian computations in domains not previously
attempted. It is set within Europe's highest ranked computer and communication
sciences faculty at EPFL, one of the leading technical universities worldwide,
with ample opportunities for collaborations at highest international rank.

EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers
away from the city of Geneva. Salaries are internationally competitive.


Applicants are expected to have finished, or be about to finish their
Ph.D. degrees. They must have an exceptional background in probabilistic
machine learning, and a firm grasp of approximate Bayesian machine learning
and/or advanced (medical) image processing. A strong track record of
publications at top ML or CV conferences (NIPS, ICML, UAI, JMLR, CVPR, ICCV,
PAMI, IJCV) and/or top-ranked (medical) image processing journals is essential.
Further pluses are strong scientific programming skills (C++, Matlab), prior
exposure to (medical) image/signal processing practice.
The working language at EPFL is English (decent skills essential), French is
not required.


Please send your applications by email to
Prof. Matthias Seeger (matthias.seeger(at)
Make sure to include:
- Statement of interest
- Curriculum vitae
- List of publications (add copies of 2-3 strongest papers in the area of
interest of this call)
- Contact details for three references

The deadline for applications is

January 15, 2011

Candidates who happen to attend the forthcoming Neural Information Processing
Systems conference (Vancouver, December 2010), should make themselves known
to Matthais Seeger there.