EVENT

JFLI seminar on "Kolmogorov complexity : what if prediction was just about compression? ", by Laurent Bienvenu, CNRS research scientist

We are pleased to inform you about the upcoming seminar by Laurent Bienvenu, CNRS research scientist titled : "Kolmogorov complexity : what if prediction was just about compression?" Everyone interested is cordially invited to attend!

Title:

Kolmogorov complexity : what if prediction was just about compression?

Abstract:

Kolmogorov complexity was introduced in the 1960s in the independent works of Chaitin, Kolmogorov and Solomonoff. It is often presented from the point of view of the first two, that is, as a measure of quantity of information via ``optimal compression". But Solomonoff's approach, based on prediction by inference, has seen a revived interest due to the recent advances in automated learning. This talk will be an introduction to Kolmogorov complexity from both of these angles with, time permitting, a glimpse of some recent works and open questions.

Speaker Bio:

Laurent Bienvenu , CNRS research scientist and associate member of the JFLI

Time/Date:

10:30-12:00 / Monday, June. 24 , 2024

Place:

Room 1210, NII

Contact:

If you would like to join, please contact by email.
Email : boudin[at]nii.ac.jp

Link:

Japanese-French Laboratory for Informatics