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
Recent Publications
Debiasing the Elastic Net for models with interactions
F. Bascou, S. Lèbre and J. Salmon (2020).
Journées de Statistique
[BibTeX]
@inproceedings{Bascou_Lebre_Salmon20,
author = {F. Bascou and S. Lèbre and J. Salmon},
booktitle = {Journées de Statistique},
pdf = {http://josephsalmon.eu/papers/JDS2020.pdf},
title = {Debiasing the Elastic Net for models with interactions},
year = {2020}
}
Implicit differentiation of Lasso-type models for hyperparameter optimization
Q. Bertrand, Q. Klopfenstein, M. Blondel, S. Vaiter, A. Gramfort and J. Salmon (2020).
ICML
[Code]
[BibTeX]
@inproceedings{Bertrand_Klopfenstein_Blondel_Vaiter_Gramfort_Salmon20,
author = {Q. Bertrand and Q. Klopfenstein and M. Blondel and S. Vaiter and A. Gramfort and J. Salmon},
booktitle = {ICML},
comment = { [Code] },
pdf = {https://arxiv.org/pdf/2002.08943.pdf},
title = {Implicit differentiation of Lasso-type models for hyperparameter optimization},
year = {2020}
}
Implicit differentiation of Lasso-type models for hyperparameter optimization
Q. Bertrand, Q. Klopfenstein, M. Blondel, S. Vaiter, A. Gramfort and J. Salmon (2020).
CAP
[Code]
[BibTeX]
@inproceedings{Bertrand_Klopfenstein_Blondel_Vaiter_Gramfort_Salmon20b,
author = {Q. Bertrand and Q. Klopfenstein and M. Blondel and S. Vaiter and A. Gramfort and J. Salmon},
booktitle = {CAP},
comment = { [Code] },
pdf = {https://arxiv.org/pdf/2002.08943.pdf},
title = {Implicit differentiation of Lasso-type models for hyperparameter optimization},
year = {2020}
}
Support recovery and sup-norm convergence rates for sparse pivotal estimation
Q. Bertrand, M. Massias, A. Gramfort and J. Salmon (2020).
AISTATS
[BibTeX]
@inproceedings{Massias_Bertrand_Gramfort_Salmon20,
author = {Q. Bertrand and M. Massias and A. Gramfort and J. Salmon},
booktitle = {AISTATS},
pages = {2655--2665},
pdf = {https://arxiv.org/pdf/2001.05401.pdf},
title = {Support recovery and sup-norm convergence rates for sparse pivotal estimation},
year = {2020}
}
Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso
J.-A. Chevalier, A. Gramfort, J. Salmon and B. Thirion (2020).
NeurIPS
[BibTeX]
@inproceedings{Chevalier_Gramfort_Salmon_Thirion20,
author = {J.-A. Chevalier and A. Gramfort and J. Salmon and B. Thirion},
booktitle = {NeurIPS},
pdf = {https://arxiv.org/pdf/2009.14310.pdf},
title = {Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso},
year = {2020}
}
@techreport{Chevalier_Nguyen_Varoquaux_Salmon_Thirion20,
author = {J.-A. Chevalier and T.-B. Nguyen and G. Varoquaux and J. Salmon and B. Thirion},
journal = {ArXiv e-prints},
title = {Decoding with Confidence: Statistical Control on Decoder Maps},
year = {2020}
}
Block based refitting in $\ell_12$ sparse regularisation
C.-A. Deledalle, N. Papadakis, J. Salmon and S. Vaiter (2020).
J. Math. Imaging Vis.
.
[BibTeX]
@article{Deledalle_Papadakis_Salmon_Vaiter19b,
author = {C.-A. Deledalle and N. Papadakis and J. Salmon and S. Vaiter},
journal = {J. Math. Imaging Vis.},
pdf = {https://arxiv.org/pdf/1910.11186.pdf},
title = {Block based refitting in $\ell_{12}$ sparse regularisation},
year = {2020}
}
Contact
News
- October 2020: talk at GdR MIA Thematic day on Non-Convex Sparse Optimization (Toulouse, France) "Screening Rules for Lasso with Non-Convex Sparse Regularizers" slides and a bit on BenchOpt, a new package to simplify, make more transparent and more reproducible comparisons between optimization algorithms
- June 2020: New paper accepted to ICML "Implicit differentiation of Lasso-type models for hyperparameter optimization" with Q. Bertrand, Q. Klopfenstein, M. Blondel, S. Vaiter and A. Gramfort, code
- January 2020: New paper accepted to AISTATS "Support recovery and sup-norm convergence rates for sparse pivotal estimation" with Q. Bertrand, M. Massias and A. Gramfort, code
- December 2019: The AI chair proposal CaMeLOt (CooperAtive MachinE Leanrning and OpTimization) has been selected by the ANR. Open PhD and postdoc positions will be published soon (location: Montpellier) Do not hesitate to contact me for additional information
- September 2019: New paper accepted at NeurIPS 2019, joint work with Q. Bertrand, M. Massias and A. Gramfort. "Handling correlated and repeated measurements with the smoothed Multivariate square-root Lasso" arxiv, code
- May 2019 : Workshop in Montpellier Graph signals : learning and optimization perspectives
- February 2019: New preprint out, joint work with A. Parmentier, V. Cohen, V. Leclère and G. Obozinski. "Mathematical programming for influence diagrams " arxiv.
- "Celer: a Fast Solver for the Lasso with Dual Extrapolation", accepted to ICML2018; code and companion paper called (pdf, slides). Joint work with Mathurin Massias and Alexandre Gramfort
- classgrade: an open source project for peer grading, mostly developped by C. Marini. In the process of being merged into: Peeramid.
Team
PhD Students
- Camille Garcin co-supervised by Alexis Joly: 2020-2023?
- Emmanuel Pilliat co-supervised by Nicolas Verzelen and Alexandra Carpentier : 2020-2023?
- Hashem Ghanem co-supervised by Samuel Vaiter and Nicolas Keriven: 2020-2023?
- Florent Bascou co-supervised by Sophie Lèbre: 2019-2022?
- Damien Blanc co-supervised by Benjamin Charlier and funded by Quantacell: 2019-2022?
- Quentin Bertrand co-supervised by Alexandre Gramfort 2018-2021?
- Nidham Gazagnadou co-supervised by Robert Gower 2018-2021?
- Jérôme-Alexis Chevalier co-supervised by Bertrand Thirion 2017-2020?
Alumni
- Mathurin Massias[PhD 2016-2019], co-supervised by Alexandre Gramfort: 2016-2019 (now at Università di Genova, Italy)
- Evgenii Chzhen [PhD 2016-2019], co-supervised by Mohamed Hebiri (now at Université Paris-Sud)
- Eugene Ndiaye [PhD, 2015-2018], co-supervised by Olivier Fercoq (now at Riken Institute, Japan)
- Jean Lafond [PhD, 2013-2016] co-supervised by Éric Moulines (now at Cubist Systematic, UK)
- Igor Colin [PhD, 2013-2016] co-supervised by Stéphan Clémençon and funded by Streamwide (now at Huawei)
- Jair Montoya [Post Doc, 2016-2017], co-supervised by Olivier Fercoq
- Thierry Guillemot (now at Rythm Inc.) Engineer, co-supervised by Alexandre Gramfort, 2016
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:
- 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.
- 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.
- 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