Welcome to my homepage. I am a researcher working on machine learning and statistics. Until recently, I lived in the Netherlands, but now I have…

Gone to Paris!

I’ve just been awarded a Rubicon grant by the Dutch science foundation to go to Paris, and do a postdoc with famous learning theorist Pascal Massart.

We are going to develop new statistical techniques that will allow scientists to work with models that are simplifications of reality, because often the real world is just too complicated to allow anything but simplified explanations.

Research Interests

My main topics of interest are currently:

• Information Theory in Statistics, MDL
• (Bayesian) Model Selection
• Online Learning
• Learning Rates and Optimal Scale Factors for Penalties

See also my publications. The first chapter of my PhD thesis provides a general introduction to the minimum description length (MDL) principle.

Contact Information

Dr. T.A.L. van Erven
tim No spam, please @timvanerven. No really, no spam nl
Bâtiment 425, Room: 102

Département de Mathématiques
Université Paris-Sud
91405 Orsay Cedex
France