research
∙
07/05/2023
Implicit Differentiation for Hyperparameter Tuning the Weighted Graphical Lasso
We provide a framework and algorithm for tuning the hyperparameters of t...
share
research
∙
10/26/2022
Coordinate Descent for SLOPE
The lasso is the most famous sparse regression and feature selection met...
research
∙
04/16/2022
Beyond L1: Faster and Better Sparse Models with skglm
We propose a new fast algorithm to estimate any sparse generalized linea...
research
∙
02/01/2022
Iterative regularization for low complexity regularizers
Iterative regularization exploits the implicit bias of an optimization a...
research
∙
05/04/2021
Implicit differentiation for fast hyperparameter selection in non-smooth convex learning
Finding the optimal hyperparameters of a model can be cast as a bilevel ...
research
∙
11/19/2020
Anderson acceleration of coordinate descent
Acceleration of first order methods is mainly obtained via inertial tech...
research
∙
06/17/2020
Implicit regularization for convex regularizers
We study implicit regularization for over-parameterized linear models, w...
research
∙
02/29/2020
Dimension-free convergence rates for gradient Langevin dynamics in RKHS
Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracte...
research
∙
01/15/2020
Support recovery and sup-norm convergence rates for sparse pivotal estimation
In high dimensional sparse regression, pivotal estimators are estimators...
research
∙
07/12/2019
Dual Extrapolation for Sparse Generalized Linear Models
Generalized Linear Models (GLM) form a wide class of regression and clas...
research
∙
05/27/2019
Learning step sizes for unfolded sparse coding
Sparse coding is typically solved by iterative optimization techniques, ...
research
∙
02/07/2019
Concomitant Lasso with Repetitions (CLaR): beyond averaging multiple realizations of heteroscedastic noise
Sparsity promoting norms are frequently used in high dimensional regress...
research
∙
05/27/2017
Generalized Concomitant Multi-Task Lasso for sparse multimodal regression
In high dimension, it is customary to consider Lasso-type estimators to ...
research
∙
03/21/2017