In the last decade, there have been an increasing convergence of interest and methods between theoretical physics and fields as diverse as probability, machine learning, optimization and compressed sensing. In particular, many theoretical and applied works in statistical physics and computer science have relied on the use of message passing algorithms and their connection to statistical physics of glasses and spin glasses. The aim of this school, especially adapted to PhD students, post-docs, and young researchers, is to present the background necessary for entering this fast developing field.

The Les Houches school of physics has long and well known history of forming generations of young researchers on the frontiers of their fields. Our school is aimed primarily at the growing audience of theoretical physicists interested in machine learning and high-dimensional data analysis, and colleagues from other fields interested in this interface. We will cover basics and frontiers of high-dimensional statistics, machine learning, theory of computing and learning, relevant mathematics and probability theory. We will focus in particular on methods of statistical physics and their results in the context of current questions and theories related to the before-mentioned fields. The school will also cover examples of applications of machine learning methods in physics research, as well as other emerging applications of wide interest. Open questions and directions will be presented as well.

Courses in the school will consist of several lectures of 90 minutes each -- 1 lecture/day over typically 5 days, but shorter or longer series are possible, we have flexibility in that respect. The lectures should be aimed at graduate level of theoretical sciences ---blackboard lectures are preferred in Les Houches. The target audience will be Phd students and post-docs from leading groups around the world.

Download the poster ofthe conference