Florent Krzakala is a professor at Sorbonne Université and a Researcher at Ecole Normale Superieure in Paris. His research interests include Statistical Physics, Machine Learning, Statistics, Computer Science and Computational Optics. He leads the SPHINX “Statistical PHysics of INformation eXtraction” team in Ecole Normale in Paris, and is the holder of the CFM-ENS Datascience chair. He is also the funder and scientific advisor of the startup Lighton.

- Professor UPMC and Researcher at Ecole Normale Superieure, Paris, Since 2013
- Member of the Insitut Universitaire de France, Since 2015
- Holder of the chair CFM-ENS on datascience, Since 2016
- Visiting Professor @ Duke University, 2018
- Visiting Scientist @ Simons Institute in Berkeley, 2016
- Visiting Scientist @ Los Alamos National Labs, 2008
- Maitre de Conference (Associate Professor) in ESPCI Paristech, 2004 - 2013

- Statistical Physics
- Machine learning
- Random Optimization Problems
- Inference on graphs
- Information theory
- Computational optics

Postdoc, 2004

Roma, La Sapienza

PhD in Statistical Physics, 2002

Orsay, Paris XI

MSc in Physics, 1999

Orsay, Paris XI

Current or recent classes

Lecture given in the international master Physics of Complex Systems on computational science

An introductory pratical course by Florent Krzakala and Antoine Baker, Ecole Doctorale EDPIF 2019

A set of Lectures given at Duke in 2018 by Lenka Zdeborova and Florent Krzakala

… and where to find them

Quickly discover relevant content by filtering publications.

In this work we analyse quantitatively the interplay between the loss landscape and performance of descent algorithms in a prototypical …

We introduce a generalized version of phase retrieval called multiplexed phase retrieval. We want to recover the phase of …

Generalized linear models (GLMs) are used in high-dimensional machine learning, statistics, communications, and signal processing. In …

Approximate message passing algorithm enjoyed considerable attention in the last decade. In this paper we introduce a variant of the …

Consider a population consisting of $n$ individuals, each of whom has one of $d$ types (e.g., blood types, in which case $d=4$). We are …