## 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.