KRZAKALA Florent

Statistical learning and statistical physics

florent.krzakala [at] ens.fr

Florent Krzakala

Short bio

Florent Krzakalais a professor at Sorbonne University and a group leader at Laboratoire de Physique at Ecole Normale Supérieure. After a PhD in Physics in Paris XI, he held different positions at ESPCI in Paris, University of Roma La Sapienza and visiting positions at the Simons Institute for the Theory of Computing (Berkeley), Duke University, Tokyo Institute of Technology, and Los Alamos National Labs. He is a fellow of the Institut Universitaire de France, a recipient of an ERC Grant, an associate editor for the Journal of Statistical Mechanics, is the executive committee for the Data Science chair at ENS, and the scientific advisor of the startup Lighton.

Topics of interest

Machine learning, Statistical physics, Random Optimization, information theory, computational optics, quantum computing

Project in Prairie

Florent Krzakala’s focus will be on the interaction between physics and machine learning: he will address fundamental questions on statistical learning using approaches inspired from statistical mechanics, and he will study the application of machine learning technics to fundamental problems in physics.

Quote

The discussions between statistical physics and machine learning disciplines has a long history, and its success is reflected even in the machine learning terminology (“Boltzmann machine”, “entropy, energy and free energy”, “mean field”…). This connection is now witnessing an impressive revival, resulting in new algorithms and new methods of analysis. One of my goal is to investigate how these ideas can help to understand models and learning algorithms used in machine learning and high-dimensional statistics.

BIROLI Giulio

Physics

giulio.biroli [at] ens.fr / Twitter: @GiulioBiroli

Giulio Biroli

Short bio

Professor of theoretical physics at ENS Paris (2018-). Research director at IPhT CEA (2002-2018). Associate professor at the Ecole Polytechnique (2010-2015). DIrector of the ICFP Master (2019-), director of the Beg Rohu Summer School (2008-). Editor in Chief of Journal of Statistical Physics. PI of the Simons collaboration «Cracking The Glass Problem», ERC Consolidator Grant 2011, Prix d’Aumale 2018, Young Scientist award in statistical physics 2007.

Topics of interest

Physics, machine learning, complex systems

Project in Prairie

Giulio Biroli will create and promote a strong synergetic activity combining physics and machine learning. He will develop a physically based theoretical approach to deep learning and apply machine learning methods to analyse complex dynamics of physical systems. He will organize a reference annual summer school-workshop on machine learning and physics.

Quote

Methodological and conceptual progresses obtained in the last decades in statistical physics and in probability theory, in particular on the analysis of high-dimensional random landscapes, on high-dimensional out of equilibrium dynamics, and on disordered systems, provide theoretical frameworks to tackle difficult challenges in AI. At the same time, AI offers new ways of studying physical systems. This is just the right time to build up on these concurrent opportunities, and develop a strong synergy combining physics and machine learning.