I am now freelance data scientist (uteal, sancare). Before that I was lead data scientist at Kayrros, working on new analytics for energy markets. I also did a post-doc at Institut Louis Bachelier, where I worked on machine learning projects involving large datasets from the industry (e.g. fraud detection for a major French retail bank). I did my Ph.D. studies at ENS and Ecole Polytechnique, in the Sierra Team and CMAP, advised by Alexandre d'Aspremont and Francis Bach.

My first name is pronounced "Fayvel" (like the figure "5" and then "l").

email: firstname.lastname@gmail.com

Working papers

Learning with Clustering Penalties

Refeered publications

SerialRank: Spectral Ranking Using Seriation
Fajwel Fogel, Alexandre d'Aspremont, Milan Vojnovic.
In NIPS 2014, extended version to appear in JMLR.

Convex Relaxations for Permutation Problems
Fajwel Fogel, Rodolphe Jenatton, Francis Bach, Alexandre d'Aspremont.
In NIPS 2013, extended version in SIAM Journal on Matrix Analysis and Applications.

Phase Retrieval for Imaging Problems
Fajwel Fogel, Irène Waldspurger, Alexandre d'Aspremont.
To appear in Mathematical Programming Computation.

Thesis, software...

Ph.D. thesis: Convex and Spectral Relaxations for Phase Retrieval, Seriation and Ranking

NMF add-on for Orange (visual programming open source software for machine learning).


ENSAE ParisTech, 2013-2014. Teaching assistant for convex optimization.

Short Bio

Lead data scientist at Kayrros, 2016.
Post-doc at Institut Louis Bachelier, 2015-2016.
PhD in applied mathematics, SIERRA project-team, Ecole Polytechnique, Paris, 2012-2015.
Visiting researcher, Microsoft Research, Cambridge UK, Spring 2014.
Master of Science in Operations Research, Columbia University, New York, 2011-2012.
ENSAE ParisTech, Paris, 2008-2012.
Lycée Henri IV, Paris, 2006-2008.