59 citations · 443 across the 46 of their papers we have counts for
9 papers · 1 filter
On Lasso refitting strategies
Evgenii Chzhen, Mohamed Hebiri, Joseph Salmon
A well-know drawback of l_1-penalized estimators is the systematic shrinkage of the large coefficients towards zero. A simple remedy is to treat Lasso as a model-selection procedur…
A sharp oracle inequality for Graph-Slope
Pierre C Bellec, Joseph Salmon, Samuel Vaiter
Following recent success on the analysis of the Slope estimator, we provide a sharp oracle inequality in term of prediction error for Graph-Slope, a generalization of Slope to sign…
On the benefits of output sparsity for multi-label classification
Evgenii Chzhen, Christophe Denis, Mohamed Hebiri +1
The multi-label classification framework, where each observation can be associated with a set of labels, has generated a tremendous amount of attention over recent years. The moder…
CLEAR: Covariant LEAst-square Re-fitting with applications to image restoration
C-A. Deledalle, N. Papadakis, J. Salmon +1
In this paper, we propose a new framework to remove parts of the systematic errors affecting popular restoration algorithms, with a special focus for image processing tasks. Genera…
On debiasing restoration algorithms: applications to total-variation and nonlocal-means
Charles-Alban Deledalle, Nicolas Papadakis, Joseph Salmon
Bias in image restoration algorithms can hamper further analysis, typically when the intensities have a physical meaning of interest, e.g., in medical imaging. We propose to suppre…
Probabilistic low-rank matrix completion on finite alphabets
Jean Lafond, Olga Klopp, Eric Moulines +1
The task of reconstructing a matrix given a sample of observedentries is known as the matrix completion problem. It arises ina wide range of problems, including recommender systems…
Adaptive Multinomial Matrix Completion
Olga Klopp, Jean Lafond, Eric Moulines +1
The task of estimating a matrix given a sample of observed entries is known as the \emph{matrix completion problem}. Most works on matrix completion have focused on recovering an u…
Oracle inequalities and minimax rates for non-local means and related adaptive kernel-based methods
Ery Arias-Castro, Joseph Salmon, Rebecca Willett
This paper describes a novel theoretical characterization of the performance of non-local means (NLM) for noise removal. NLM has proven effective in a variety of empirical studies,…
Sharp Oracle Inequalities for Aggregation of Affine Estimators
Arnak Dalalyan, Joseph Salmon
We consider the problem of combining a (possibly uncountably infinite) set of affine estimators in non-parametric regression model with heteroscedastic Gaussian noise. Focusing on…