4 papers
On The Linear Convergence of Bregman Proximal Gradient Methods with Applications to Kullback--Leibler regression
Jonathan Chirinos-RodrÃguez, Christian Daniele, Cédric Févotte +1
Bregman Proximal Gradient methods (BPGM) exploit the underlying geometry of the objective function through a carefully chosen mirror map. In this work, we introduce a novel notion…
Optimization landscape of -Bregman relaxations
Jonathan Chirinos-RodrÃguez, Cédric Févotte, Emmanuel Soubies
In this paper, we study (noisy) linear systems, and their -regularized optimization problems, coupled with general data fidelity terms. Recent approaches for solving this c…
Exact continuous relaxations of l0-regularized criteria with non-quadratic data terms
M'hamed Essafri, Luca Calatroni, Emmanuel Soubies
We propose a new class of exact continuous relaxations of l0-regularized criteria involving non-quadratic data terms such as the Kullback-Leibler divergence and the logistic regres…
Box-constrained L0 Bregman-relaxations
Mhamed Essafri, Luca Calatroni, Emmanuel Soubies
Regularization using the L0 pseudo-norm is a common approach to promote sparsity, with widespread applications in machine learning and signal processing. However, solving such prob…