86 citations · 685 across the 45 of their papers we have counts for
5 papers · 1 filter
A Coordinate Descent Primal-Dual Algorithm with Large Step Size and Possibly Non Separable Functions
Olivier Fercoq, Pascal Bianchi
This paper introduces a coordinate descent version of the Vũ-Condat algorithm. By coordinate descent, we mean that only a subset of the coordinates of the primal and dual iterates…
A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Convex Minimization
Quoc Tran-Dinh, Olivier Fercoq, Volkan Cevher
We propose a new first-order primal-dual optimization framework for a convex optimization template with broad applications. Our optimization algorithms feature optimal convergence…
GAP Safe screening rules for sparse multi-task and multi-class models
Eugene Ndiaye, Olivier Fercoq, Alexandre Gramfort +1
High dimensional regression benefits from sparsity promoting regularizations. Screening rules leverage the known sparsity of the solution by ignoring some variables in the optimiza…
Mind the duality gap: safer rules for the Lasso
Olivier Fercoq, Alexandre Gramfort, Joseph Salmon
Screening rules allow to early discard irrelevant variables from the optimization in Lasso problems, or its derivatives, making solvers faster. In this paper, we propose new versio…
SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization
Zheng Qu, Peter Richtárik, Martin Takáč +1
We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subse…