Optimality of 1-norm regularization among weighted 1-norms for sparse recovery: a case study on how to find optimal regularizations
TRAONMILIN, Yann
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bordeaux [IMB]
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bordeaux [IMB]
VAITER, Samuel
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bourgogne [Dijon] [IMB]
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bourgogne [Dijon] [IMB]
TRAONMILIN, Yann
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bordeaux [IMB]
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bordeaux [IMB]
VAITER, Samuel
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bourgogne [Dijon] [IMB]
< Reduce
Centre National de la Recherche Scientifique [CNRS]
Institut de Mathématiques de Bourgogne [Dijon] [IMB]
Language
en
Communication dans un congrès
This item was published in
Journal of Physics: Conference Series, Journal of Physics: Conference Series, 8th International Conference on New Computational Methods for Inverse Problems, 2018-05-25, Paris. 2018, vol. 1131, p. conference 1
IOP Science
English Abstract
The 1-norm was proven to be a good convex regularizer for the recovery of sparse vectors from under-determined linear measurements. It has been shown that with an appropriate measurement operator, a number of measurements ...Read more >
The 1-norm was proven to be a good convex regularizer for the recovery of sparse vectors from under-determined linear measurements. It has been shown that with an appropriate measurement operator, a number of measurements of the order of the sparsity of the signal (up to log factors) is sufficient for stable and robust recovery. More recently, it has been shown that such recovery results can be generalized to more general low-dimensional model sets and (convex) regularizers. These results lead to the following question: to recover a given low-dimensional model set from linear measurements, what is the "best" convex regularizer? To approach this problem, we propose a general framework to define several notions of "best regularizer" with respect to a low-dimensional model. We show in the minimal case of sparse recovery in dimension 3 that the 1-norm is optimal for these notions. However, generalization of such results to the n-dimensional case seems out of reach. To tackle this problem, we propose looser notions of best regularizer and show that the 1-norm is optimal among weighted 1-norms for sparse recovery within this framework.Read less <
Origin
Hal imported