Recent Publications


Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning
P.-A. Bannier, Q. Bertrand, J. Salmon and A. Gramfort (2021).
Medical imaging meets NeurIPS (Workshop) [BibTeX] 

@inproceedings{Bannier_Bertrand_Salmon_Gramfort2021,
 author = {P.-A. Bannier and Q. Bertrand and J. Salmon and A. Gramfort},
 booktitle = {Medical imaging meets NeurIPS (Workshop)},
 pdf = {http://josephsalmon.eu/papers/Bannier_etal2021.pdf},
 title = {Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning},
 year = {2021}
}

ElasticNet avec gestion des interactions et débiaisage
F. Bascou, S. Lèbre and J. Salmon (2021).
EGC [BibTeX] 

@inproceedings{Bascou_Lebre_Salmon21,
 author = {F. Bascou and S. Lèbre and J. Salmon},
 booktitle = {EGC},
 pdf = {https://editions-rnti.fr/render_pdf.php?p=1002656},
 title = {ElasticNet avec gestion des interactions et débiaisage},
 year = {2021}
}

Implicit differentiation for fast hyperparameter selection in non-smooth convex learning
Q. Bertrand, Q. Klopfenstein, M. Massias, M. Blondel, S. Vaiter, A. Gramfort and J. Salmon (2021).
[BibTeX] 

@techreport{Bertrand_Klopfenstein_Massias_Blondel_Vaiter_Gramfort_Salmon21,
 author = {Q. Bertrand and Q. Klopfenstein and M. Massias and M. Blondel and S. Vaiter and A. Gramfort and J. Salmon},
 eprint = {2105.01637},
 journal = {arXiv e-prints},
 pages = {arXiv:2105.01637},
 pdf = {https://arxiv.org/pdf/2105.01637},
 primaryclass = {stat.ML},
 title = {{Implicit differentiation for fast hyperparameter selection in non-smooth convex learning}},
 year = {2021}
}

Decoding with Confidence: Statistical Control on Decoder Maps
J.-A. Chevalier, T.-B. Nguyen, G. Varoquaux, J. Salmon and B. Thirion (2021).
Neuroimage . [BibTeX] 

@article{Chevalier_Nguyen_Varoquaux_Salmon_Thirion20,
 author = {J.-A. Chevalier and T.-B. Nguyen and G. Varoquaux and J. Salmon and B. Thirion},
 journal = {Neuroimage},
 pages = {117921},
 pdf = {https://www.sciencedirect.com/science/article/pii/S1053811921001981},
 title = {Decoding with Confidence: Statistical Control on Decoder Maps},
 year = {2021}
}

Block based refitting in $\ell_12$ sparse regularisation
C.-A. Deledalle, N. Papadakis, J. Salmon and S. Vaiter (2021).
J. Math. Imaging Vis. 63: (216-236). [BibTeX] 

@article{Deledalle_Papadakis_Salmon_Vaiter21,
 author = {C.-A. Deledalle and N. Papadakis and J. Salmon and S. Vaiter},
 journal = {J. Math. Imaging Vis.},
 pages = {216-236},
 pdf = {https://arxiv.org/pdf/1910.11186.pdf},
 title = {Block based refitting in $\ell_{12}$ sparse regularisation},
 volume = {63},
 year = {2021}
}

Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution
C. Garcin, A. Joly, P. Bonnet, A. Affouard, J.-C. Lombardo, M. Chouet, M. Servajean, T. Lorieul and J. Salmon (2021).
Neurips, Datasets and Benchmarks Track [BibTeX] 

@inproceedings{Garcin_Joly_Bonnet_Affouard_Lombardo_Chouet_Servajean_Lorieul_Salmon2021,
 author = {C. Garcin and A. Joly and P. Bonnet and A. Affouard and J.-C. Lombardo and M. Chouet and M. Servajean and T. Lorieul and J. Salmon},
 booktitle = {Neurips, Datasets and Benchmarks Track},
 pdf = {https://openreview.net/pdf?id=eLYinD0TtIt},
 title = {Pl@ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution},
 year = {2021}
}

Score-based change detection for gradient-based learning machines
L. Liu, J. Salmon and Z. Harchaoui (2021).
ICASSP [BibTeX] 

@inproceedings{Liu_Salmon_Harchaoui21,
 author = {L. Liu and J. Salmon and Z. Harchaoui},
 booktitle = {ICASSP},
 pdf = {https://stat.uw.edu/sites/default/files/2019-07/tr652.pdf},
 title = {Score-based change detection for gradient-based learning machines},
 year = {2021}
}

Full list of publications

Contact

Email: joseph.salmon@umontpellier.fr

Address: IMAG, c.c. 051
Université de Montpellier
Place Eugène Bataillon
34095 Montpellier Cedex 5
(office 415, building 9)

Phone: +33 4 67 14 35 19

News

Team

PhD Students



Alumni

Joining my team?

I am always looking for outstanding and highly motivated people to join my team as interns, PhD students, post-doctorates or research engineers in the following areas:

  • optimization for machine learning (including federated learning, privacy, etc.)
  • high dimensional and robust statistics

I always have open positions for outstanding applicants. The application process is light:

  1. Send me an email with your CV, transcript of most recent grades (for interns and PhD students) and explain in a paragraph why you are interested to join my group.
  2. After preliminary feedback on my side, I will ask you to secure two reference letters (one is enough for interns or PhD students) to be sent directly to me.
  3. At this stage an interview (possibly online) will be arranged to double check your skills and profile compatibility.

Short Bio

Since 2018, I am a full professor at Université de Montpellier and an associate member at INRIA Parietal Team. For the spring and summer quarters 2018, I was a visiting assistant professor at UW, Statistics departement. From 2012 to 2018 I was an assistant professor at Telecom ParisTech. Back in 2011 and 2012, I was a post-doctoral Associate at Duke university working with Rebecca Willett.

In 2010, I finished my PHD in statistics and image processing under the supervision of Dominique Picard and Erwan Le Pennec at the Laboratoire de Probabilités et de Modélisation Aléatoire, now LPSM, in Université Paris Diderot.

Software

  • BenchOpt: package to simplify, make more transparent and more reproducible comparisons between optimization algorithms

  • Celer: a fast Lasso solver, code of the associated ICML2018 paper "Dual Extrapolation for Faster Lasso Solvers" (pdf, slides)

  • sparse-ho: a fast hyper-parameter package to select the best Lasso parameter efficiently, code of the associated ICML2020 paper "Implicit differentiation of Lasso-type models for hyperparameter optimization" (pdf)
  • matlab toolboxes for statistics and image processing (this is legacy)

More on my Github Page

Open positions in my lab

This list is fuzzy so please contact me directly for potential opportunities (post-doc, phd thesis, internship)

Teaching / courses

HLMA408 - Traitement de données pour l'écologie (2018-2019)
HMMA237 - Séries temporelles avancées (2018-2019)
HMMA238 - Bonnes pratiques en programmation (2018-2019)
HLMA310 - Logiciels scientifiques (2018-2019)
HMMA308 - Apprentissage statistique (2018-2019)
STAT593 - Robust statistics (2018-2019)
M2MO - Statistical Learning (2013-2018)
SD204 - Linear models (2016-2018)
MDI720 - Modèles linéaires (2013-2018)
CR12 - Machine Learning (2013-2015)
SD3 - Statistiques Descriptives (2010-2011)
M53010 - Économétrie (2009-2010)

Full list of courses

Talks

Full list of talks, with slides and possibly videos when recorded.

Miscellaneous

Here (Miscellaneous), you will find some (math)art and other distractions.