12th December 2018 : Postdoc Ens Paris / Algorithms for Inference and Learning

Dear friends and colleagues,

I would like to invite applications for postdoctoral positions in my group in Ecole Normale in Paris. More information on http://postdoc.krzakala.org/

The positions are funded by the ANR-FNS French-Swiss grant PAIL (PIs : Florent Krzakala ENS-Paris, Nicolas Macris EPFL-Lausanne). The appointments are intended to start anytime from now to in the fall of 2019 and will be for 2 years.

This project on Phase diagrams and Algorithms for Inference and Learning aims at developing a better theoretical understanding of the recent advances in machine learning and high-dimensional statistics that have had a tremendous impact but call for more principled, and ideally rigorous, justifications.

This goal will be pursued in this project by building on the fruitful interplay between statistical mechanics of disordered systems, discrete mathematics and computer science that has produced a number of important results in the related fields of constraint satisfaction problems and probabilistic inference. The project is developed with Guilhem Semerjian and in collaboration with Marc Mezard, Lenka Zdeborova (CEA Saclay) and many groups in the Parisian region.

This project places an emphasis on interdisciplinarity, and aims to achieve progress by bringing together postdocs with different scientific backgrounds. More specifically, the candidates can come from different areas (Statistics and probability, theoretical physics, signal processing, applied mathematics, statistical physics, information theory, machine learning and neural networks) and are expected to bring their expertise. Successful candidates will thus conduct a vigorous research program within the scope of the project.

The members of the group also keep close contacts with other researchers of the Ecole Normale Superieure, of the University Paris-Sud and of the CEA Saclay, all of them based closed by. The ENS is conveniently located in the very center of Paris. The positions are endowed with travel and computing resources.

Keywords: Probability and statistics, Machine Learning, Signal processing, information theory, graphical models, Bayesian inference, compressed sensing, error correcting codes, spatial coupling, Belief Propagation, Message Passing, Tomography. Statistical physics – glasses, spin glasses, random optimization problems, cavity method, replica method – c, c++, matlab, julia, python.

Deadline: Apply before Jan 15, 2019 

To apply, and for further information: florent.krzakala@ens.fr and http://postdoc.krzakala.org 

The candidates should send their detailed cv (including list of publication, presentations, citations etc.), and 1 page letter of motivation explaining why they want to work on this subject, what is their related experience, and present a short project. Preselected candidates should be ready to provide two letters of recommendation at a later stage.