Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Herzet, Cedric"'
We consider the resolution of learning problems involving $\ell_0$-regularization via Branch-and-Bound (BnB) algorithms. These methods explore regions of the feasible space of the problem and check whether they do not contain solutions through "pruni
Externí odkaz:
http://arxiv.org/abs/2406.03504
In this paper, we put forth a novel framework (named ``RYU'') for the construction of ``safe'' balls, i.e. regions that provably contain the dual solution of a target optimization problem. We concentrate on the standard setup where the cost function
Externí odkaz:
http://arxiv.org/abs/2312.00640
We introduce a new methodology dubbed ``safe peeling'' to accelerate the resolution of L0-regularized least-squares problems via a Branch-and-Bound (BnB) algorithm. Our procedure enables to tighten the convex relaxation considered at each node of the
Externí odkaz:
http://arxiv.org/abs/2302.14471
In this paper, we propose a novel safe screening test for Lasso. Our procedure is based on a safe region with a dome geometry and exploits a canonical representation of the set of half-spaces (referred to as "dual cutting half-spaces" in this paper)
Externí odkaz:
http://arxiv.org/abs/2203.00987
Autor:
Elvira, Clément, Herzet, Cédric
In this paper we propose a methodology to accelerate the resolution of the so-called "Sorted L-One Penalized Estimation" (SLOPE) problem. Our method leverages the concept of "safe screening", well-studied in the literature for \textit{group-separable
Externí odkaz:
http://arxiv.org/abs/2110.11784
We present a novel screening methodology to safely discard irrelevant nodes within a generic branch-and-bound (BnB) algorithm solving the l0-penalized least-squares problem. Our contribution is a set of two simple tests to detect sets of feasible vec
Externí odkaz:
http://arxiv.org/abs/2110.07308
In this paper, we propose a procedure to accelerate the resolution of the well-known "Elastic-Net" problem. Our procedure is based on the (partial) identification of the solution support and the reformulation of the original problem into a problem of
Externí odkaz:
http://arxiv.org/abs/2110.07281
Autor:
Heas, Patrick, Herzet, Cedric
This technical note reviews sate-of-the-art algorithms for linear approximation of high-dimensional dynamical systems using low-rank dynamic mode decomposition (DMD). While repeating several parts of our article "low-rank dynamic mode decomposition:
Externí odkaz:
http://arxiv.org/abs/2108.09160
Autor:
Champagnat, Frédéric, Herzet, Cédric
In this communication, we address the problem of approximating the atoms of a parametric dictionary, commonly encountered in the context of sparse representations in "continuous" dictionaries. We focus on the case of translation-invariant dictionarie
Externí odkaz:
http://arxiv.org/abs/2011.14452
In this short paper we bridge two seemingly unrelated sparse approximation topics: continuous sparse coding and low-rank approximations. We show that for a specific choice of continuous dictionary, linear systems with nuclear-norm regularization have
Externí odkaz:
http://arxiv.org/abs/2009.06340