Joseph Salmon

is this you? claim profile

Assistant Professor at TELECOM ParisTech, Associate member at INRIA Parietal, Visiting assistant professor at UW, Statistics departement.

Model identification and local linear convergence of coordinate descent

For composite nonsmooth optimization problems, Forward-Backward algorith...
10/22/2020 ∙ by Quentin Klopfenstein, et al. ∙ 0 ∙ share

read it
Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso

Detecting where and when brain regions activate in a cognitive task or i...
09/29/2020 ∙ by Jérôme-Alexis Chevalier, et al. ∙ 12 ∙ share

read it
Screening Rules and its Complexity for Active Set Identification

Screening rules were recently introduced as a technique for explicitly i...
09/06/2020 ∙ by Eugene Ndiaye, et al. ∙ 7 ∙ share

read it
Provably Convergent Working Set Algorithm for Non-Convex Regularized Regression

Owing to their statistical properties, non-convex sparse regularizers ha...
06/24/2020 ∙ by Alain Rakotomamonjy, et al. ∙ 13 ∙ share

read it
Implicit differentiation of Lasso-type models for hyperparameter optimization

Setting regularization parameters for Lasso-type estimators is notorious...
02/20/2020 ∙ by Quentin Bertrand, et al. ∙ 7 ∙ share

read it
Support recovery and sup-norm convergence rates for sparse pivotal estimation

In high dimensional sparse regression, pivotal estimators are estimators...
01/15/2020 ∙ by Mathurin Massias, et al. ∙ 22 ∙ share

read it
Dual Extrapolation for Sparse Generalized Linear Models

Generalized Linear Models (GLM) form a wide class of regression and clas...
07/12/2019 ∙ by Mathurin Massias, et al. ∙ 11 ∙ share

read it
Screening Rules for Lasso with Non-Convex Sparse Regularizers

Leveraging on the convexity of the Lasso problem , screening rules help ...
02/16/2019 ∙ by Alain Rakotomamonjy, et al. ∙ 18 ∙ share

read it
Concomitant Lasso with Repetitions (CLaR): beyond averaging multiple realizations of heteroscedastic noise

Sparsity promoting norms are frequently used in high dimensional regress...
02/07/2019 ∙ by Quentin Bertrand, et al. ∙ 18 ∙ share

read it
Optimal mini-batch and step sizes for SAGA

Recently it has been shown that the step sizes of a family of variance r...
01/31/2019 ∙ by Nidham Gazagnadou, et al. ∙ 22 ∙ share

read it
Safe Grid Search with Optimal Complexity

Popular machine learning estimators involve regularization parameters th...
10/12/2018 ∙ by Eugene Ndiaye, et al. ∙ 0 ∙ share

read it
Statistical Inference with Ensemble of Clustered Desparsified Lasso

Medical imaging involves high-dimensional data, yet their acquisition is...
06/15/2018 ∙ by Jérôme-Alexis Chevalier, et al. ∙ 0 ∙ share

read it
A hierarchical Bayesian perspective on majorization-minimization for non-convex sparse regression: application to M/EEG source imaging

Majorization-minimization (MM) is a standard iterative optimization tech...
10/24/2017 ∙ by Yousra Bekhti, et al. ∙ 0 ∙ share

read it
Generalized Concomitant Multi-Task Lasso for sparse multimodal regression

In high dimension, it is customary to consider Lasso-type estimators to ...
05/27/2017 ∙ by Mathurin Massias, et al. ∙ 0 ∙ share

read it
From safe screening rules to working sets for faster Lasso-type solvers

Convex sparsity-promoting regularizations are ubiquitous in modern stati...
03/21/2017 ∙ by Mathurin Massias, et al. ∙ 0 ∙ share

read it
On the benefits of output sparsity for multi-label classification

The multi-label classification framework, where each observation can be ...
03/14/2017 ∙ by Evgenii Chzhen, et al. ∙ 0 ∙ share

read it
Gap Safe screening rules for sparsity enforcing penalties

In high dimensional regression settings, sparsity enforcing penalties ha...
11/17/2016 ∙ by Eugene Ndiaye, et al. ∙ 0 ∙ share

read it
Efficient Smoothed Concomitant Lasso Estimation for High Dimensional Regression

In high dimensional settings, sparse structures are crucial for efficien...
06/08/2016 ∙ by Eugene Ndiaye, et al. ∙ 0 ∙ share

read it
Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions

In decentralized networks (of sensors, connected objects, etc.), there i...
06/08/2016 ∙ by Igor Colin, et al. ∙ 0 ∙ share

read it
GAP Safe Screening Rules for Sparse-Group-Lasso

In high dimensional settings, sparse structures are crucial for efficien...
02/19/2016 ∙ by Eugene Ndiaye, et al. ∙ 0 ∙ share

read it
Extending Gossip Algorithms to Distributed Estimation of U-Statistics

Efficient and robust algorithms for decentralized estimation in networks...
11/17/2015 ∙ by Igor Colin, et al. ∙ 0 ∙ share

read it
GAP Safe screening rules for sparse multi-task and multi-class models

High dimensional regression benefits from sparsity promoting regularizat...
06/11/2015 ∙ by Eugene Ndiaye, et al. ∙ 0 ∙ share

read it
Mind the duality gap: safer rules for the Lasso

Screening rules allow to early discard irrelevant variables from the opt...
05/13/2015 ∙ by Olivier Fercoq, et al. ∙ 0 ∙ share

read it
Learning Heteroscedastic Models by Convex Programming under Group Sparsity

Popular sparse estimation methods based on ℓ_1-relaxation, such as the L...
04/16/2013 ∙ by Arnak S. Dalalyan, et al. ∙ 0 ∙ share

read it
A two-stage denoising filter: the preprocessed Yaroslavsky filter

This paper describes a simple image noise removal method which combines ...
08/31/2012 ∙ by Joseph Salmon, et al. ∙ 0 ∙ share

read it
Poisson noise reduction with non-local PCA

Photon-limited imaging arises when the number of photons collected by a ...
06/02/2012 ∙ by Joseph Salmon, et al. ∙ 0 ∙ share

read it
Oracle inequalities and minimax rates for non-local means and related adaptive kernel-based methods

This paper describes a novel theoretical characterization of the perform...
12/19/2011 ∙ by Ery Arias-Castro, et al. ∙ 0 ∙ share

read it

Joseph Salmon

Featured Co-authors

Alexandre Gramfort

Ichiro Takeuchi

Bertrand Thirion

Stephan Clémençon

Rebecca Willett

Aurélien Bellet

Rémi Flamary

Ery Arias-Castro

Mathieu Blondel

Alain Rakotomamonjy

Olivier Fercoq

Model identification and local linear convergence of coordinate descent

Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso

Screening Rules and its Complexity for Active Set Identification

Provably Convergent Working Set Algorithm for Non-Convex Regularized Regression

Implicit differentiation of Lasso-type models for hyperparameter optimization

Support recovery and sup-norm convergence rates for sparse pivotal estimation

Dual Extrapolation for Sparse Generalized Linear Models

Screening Rules for Lasso with Non-Convex Sparse Regularizers

Concomitant Lasso with Repetitions (CLaR): beyond averaging multiple realizations of heteroscedastic noise

Optimal mini-batch and step sizes for SAGA

Safe Grid Search with Optimal Complexity

Statistical Inference with Ensemble of Clustered Desparsified Lasso

A hierarchical Bayesian perspective on majorization-minimization for non-convex sparse regression: application to M/EEG source imaging

Generalized Concomitant Multi-Task Lasso for sparse multimodal regression

From safe screening rules to working sets for faster Lasso-type solvers

On the benefits of output sparsity for multi-label classification

Gap Safe screening rules for sparsity enforcing penalties

Efficient Smoothed Concomitant Lasso Estimation for High Dimensional Regression

Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions

GAP Safe Screening Rules for Sparse-Group-Lasso

Extending Gossip Algorithms to Distributed Estimation of U-Statistics

GAP Safe screening rules for sparse multi-task and multi-class models

Mind the duality gap: safer rules for the Lasso

Learning Heteroscedastic Models by Convex Programming under Group Sparsity

A two-stage denoising filter: the preprocessed Yaroslavsky filter

Poisson noise reduction with non-local PCA

Oracle inequalities and minimax rates for non-local means and related adaptive kernel-based methods